{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 12,
  "global_step": 63,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 0.5501871705055237,
      "learning_rate": 0.0,
      "loss": 1.21484375,
      "step": 1
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 0.5486732721328735,
      "learning_rate": 5e-05,
      "loss": 1.0947265625,
      "step": 2
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.3428894877433777,
      "learning_rate": 0.0001,
      "loss": 1.06201171875,
      "step": 3
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.19505959749221802,
      "learning_rate": 9.994033404481737e-05,
      "loss": 0.837890625,
      "step": 4
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 0.15906307101249695,
      "learning_rate": 9.97614944026565e-05,
      "loss": 0.849853515625,
      "step": 5
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.2227369248867035,
      "learning_rate": 9.946395532409847e-05,
      "loss": 0.915283203125,
      "step": 6
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.20231562852859497,
      "learning_rate": 9.904850582929111e-05,
      "loss": 0.831298828125,
      "step": 7
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.18000583350658417,
      "learning_rate": 9.851624761560943e-05,
      "loss": 0.87841796875,
      "step": 8
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.1295953094959259,
      "learning_rate": 9.786859213615221e-05,
      "loss": 0.92822265625,
      "step": 9
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.099913589656353,
      "learning_rate": 9.710725685682222e-05,
      "loss": 0.813232421875,
      "step": 10
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 0.11362982541322708,
      "learning_rate": 9.623426070191522e-05,
      "loss": 0.723876953125,
      "step": 11
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.09283869713544846,
      "learning_rate": 9.525191870029581e-05,
      "loss": 0.687744140625,
      "step": 12
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 0.10829943418502808,
      "learning_rate": 9.4162835846357e-05,
      "loss": 0.802490234375,
      "step": 13
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.10302653908729553,
      "learning_rate": 9.296990019204335e-05,
      "loss": 0.8428955078125,
      "step": 14
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.08654075115919113,
      "learning_rate": 9.167627518825651e-05,
      "loss": 0.7138671875,
      "step": 15
    },
    {
      "epoch": 0.7142857142857143,
      "eval_loss": 0.8271484375,
      "eval_runtime": 6.4521,
      "eval_samples_per_second": 0.62,
      "eval_steps_per_second": 0.155,
      "step": 15
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.11643221974372864,
      "learning_rate": 9.028539129595199e-05,
      "loss": 0.80078125,
      "step": 16
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 0.09286683052778244,
      "learning_rate": 8.88009368891734e-05,
      "loss": 0.841796875,
      "step": 17
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.08940571546554565,
      "learning_rate": 8.72268484741477e-05,
      "loss": 0.78759765625,
      "step": 18
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 0.09568110853433609,
      "learning_rate": 8.556730025037819e-05,
      "loss": 0.740478515625,
      "step": 19
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.07992596179246902,
      "learning_rate": 8.38266930414179e-05,
      "loss": 0.6640625,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.08235524594783783,
      "learning_rate": 8.200964262467657e-05,
      "loss": 0.8515625,
      "step": 21
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 0.08874722570180893,
      "learning_rate": 8.01209674912089e-05,
      "loss": 0.845703125,
      "step": 22
    },
    {
      "epoch": 1.0952380952380953,
      "grad_norm": 0.08876466751098633,
      "learning_rate": 7.81656760679424e-05,
      "loss": 0.732421875,
      "step": 23
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.08666371554136276,
      "learning_rate": 7.614895343622941e-05,
      "loss": 0.7750244140625,
      "step": 24
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 0.08446256816387177,
      "learning_rate": 7.407614758194375e-05,
      "loss": 0.6376953125,
      "step": 25
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 0.10976085066795349,
      "learning_rate": 7.195275521358334e-05,
      "loss": 0.68212890625,
      "step": 26
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.09492490440607071,
      "learning_rate": 6.978440718598757e-05,
      "loss": 0.75390625,
      "step": 27
    },
    {
      "epoch": 1.2857142857142856,
      "eval_loss": 0.787109375,
      "eval_runtime": 6.4306,
      "eval_samples_per_second": 0.622,
      "eval_steps_per_second": 0.156,
      "step": 27
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.07493570446968079,
      "learning_rate": 6.757685356832243e-05,
      "loss": 0.6959228515625,
      "step": 28
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 0.08283965289592743,
      "learning_rate": 6.533594839593081e-05,
      "loss": 0.747314453125,
      "step": 29
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.08391156792640686,
      "learning_rate": 6.306763414648311e-05,
      "loss": 0.807373046875,
      "step": 30
    },
    {
      "epoch": 1.4761904761904763,
      "grad_norm": 0.6904768943786621,
      "learning_rate": 6.07779259815948e-05,
      "loss": 0.702392578125,
      "step": 31
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 0.08848796039819717,
      "learning_rate": 5.84728957956991e-05,
      "loss": 0.6214599609375,
      "step": 32
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.06401556730270386,
      "learning_rate": 5.61586561144745e-05,
      "loss": 0.6064453125,
      "step": 33
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 0.07748808711767197,
      "learning_rate": 5.384134388552552e-05,
      "loss": 0.7080078125,
      "step": 34
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.0812332034111023,
      "learning_rate": 5.152710420430091e-05,
      "loss": 0.7474365234375,
      "step": 35
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.0721367672085762,
      "learning_rate": 4.9222074018405206e-05,
      "loss": 0.63818359375,
      "step": 36
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 0.16443495452404022,
      "learning_rate": 4.693236585351691e-05,
      "loss": 0.716552734375,
      "step": 37
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 0.09385030716657639,
      "learning_rate": 4.4664051604069214e-05,
      "loss": 0.75634765625,
      "step": 38
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.09399207681417465,
      "learning_rate": 4.2423146431677585e-05,
      "loss": 0.70263671875,
      "step": 39
    },
    {
      "epoch": 1.8571428571428572,
      "eval_loss": 0.76708984375,
      "eval_runtime": 6.4268,
      "eval_samples_per_second": 0.622,
      "eval_steps_per_second": 0.156,
      "step": 39
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.08889850974082947,
      "learning_rate": 4.021559281401244e-05,
      "loss": 0.66162109375,
      "step": 40
    },
    {
      "epoch": 1.9523809523809523,
      "grad_norm": 0.07356970012187958,
      "learning_rate": 3.804724478641667e-05,
      "loss": 0.6004638671875,
      "step": 41
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.08257210999727249,
      "learning_rate": 3.592385241805628e-05,
      "loss": 0.773681640625,
      "step": 42
    },
    {
      "epoch": 2.0476190476190474,
      "grad_norm": 0.08057400584220886,
      "learning_rate": 3.385104656377062e-05,
      "loss": 0.76123046875,
      "step": 43
    },
    {
      "epoch": 2.0952380952380953,
      "grad_norm": 0.07585829496383667,
      "learning_rate": 3.183432393205763e-05,
      "loss": 0.663818359375,
      "step": 44
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.09801910817623138,
      "learning_rate": 2.9879032508791093e-05,
      "loss": 0.7042236328125,
      "step": 45
    },
    {
      "epoch": 2.1904761904761907,
      "grad_norm": 0.09920642524957657,
      "learning_rate": 2.799035737532344e-05,
      "loss": 0.577880859375,
      "step": 46
    },
    {
      "epoch": 2.238095238095238,
      "grad_norm": 0.07839144766330719,
      "learning_rate": 2.6173306958582123e-05,
      "loss": 0.623291015625,
      "step": 47
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.09373270720243454,
      "learning_rate": 2.443269974962181e-05,
      "loss": 0.688720703125,
      "step": 48
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.07642136514186859,
      "learning_rate": 2.277315152585231e-05,
      "loss": 0.6412353515625,
      "step": 49
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.09019405394792557,
      "learning_rate": 2.1199063110826618e-05,
      "loss": 0.689453125,
      "step": 50
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.08128011226654053,
      "learning_rate": 1.9714608704048037e-05,
      "loss": 0.75537109375,
      "step": 51
    },
    {
      "epoch": 2.4285714285714284,
      "eval_loss": 0.75732421875,
      "eval_runtime": 6.4255,
      "eval_samples_per_second": 0.623,
      "eval_steps_per_second": 0.156,
      "step": 51
    },
    {
      "epoch": 2.4761904761904763,
      "grad_norm": 0.09704925864934921,
      "learning_rate": 1.8323724811743496e-05,
      "loss": 0.6483154296875,
      "step": 52
    },
    {
      "epoch": 2.5238095238095237,
      "grad_norm": 0.08347293734550476,
      "learning_rate": 1.703009980795665e-05,
      "loss": 0.577392578125,
      "step": 53
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.07354769110679626,
      "learning_rate": 1.5837164153643015e-05,
      "loss": 0.568115234375,
      "step": 54
    },
    {
      "epoch": 2.619047619047619,
      "grad_norm": 0.0844465047121048,
      "learning_rate": 1.474808129970421e-05,
      "loss": 0.66259765625,
      "step": 55
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.08416235446929932,
      "learning_rate": 1.3765739298084793e-05,
      "loss": 0.701171875,
      "step": 56
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 0.07910469174385071,
      "learning_rate": 1.2892743143177793e-05,
      "loss": 0.602294921875,
      "step": 57
    },
    {
      "epoch": 2.761904761904762,
      "grad_norm": 0.08816498517990112,
      "learning_rate": 1.2131407863847787e-05,
      "loss": 0.6751708984375,
      "step": 58
    },
    {
      "epoch": 2.8095238095238093,
      "grad_norm": 0.09950327128171921,
      "learning_rate": 1.1483752384390584e-05,
      "loss": 0.71337890625,
      "step": 59
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.09992720931768417,
      "learning_rate": 1.09514941707089e-05,
      "loss": 0.6630859375,
      "step": 60
    },
    {
      "epoch": 2.9047619047619047,
      "grad_norm": 0.0930309146642685,
      "learning_rate": 1.0536044675901534e-05,
      "loss": 0.626220703125,
      "step": 61
    },
    {
      "epoch": 2.9523809523809526,
      "grad_norm": 0.07868897914886475,
      "learning_rate": 1.0238505597343493e-05,
      "loss": 0.572509765625,
      "step": 62
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.08437960594892502,
      "learning_rate": 1.0059665955182628e-05,
      "loss": 0.737060546875,
      "step": 63
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.751953125,
      "eval_runtime": 6.4346,
      "eval_samples_per_second": 0.622,
      "eval_steps_per_second": 0.155,
      "step": 63
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 63,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.221367681340408e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}