{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04505180958101817,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006006907944135756,
      "grad_norm": 4.475499153137207,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 11.1823,
      "step": 1
    },
    {
      "epoch": 0.0006006907944135756,
      "eval_loss": 10.963411331176758,
      "eval_runtime": 73.5298,
      "eval_samples_per_second": 9.534,
      "eval_steps_per_second": 4.774,
      "step": 1
    },
    {
      "epoch": 0.0012013815888271512,
      "grad_norm": 4.378462314605713,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 11.8281,
      "step": 2
    },
    {
      "epoch": 0.0018020723832407267,
      "grad_norm": 4.241245269775391,
      "learning_rate": 5e-05,
      "loss": 10.2197,
      "step": 3
    },
    {
      "epoch": 0.0024027631776543023,
      "grad_norm": 4.603492736816406,
      "learning_rate": 4.997620553954645e-05,
      "loss": 11.4859,
      "step": 4
    },
    {
      "epoch": 0.003003453972067878,
      "grad_norm": 5.162914276123047,
      "learning_rate": 4.990486745229364e-05,
      "loss": 10.3291,
      "step": 5
    },
    {
      "epoch": 0.0036041447664814535,
      "grad_norm": 4.5874342918396,
      "learning_rate": 4.9786121534345265e-05,
      "loss": 10.4305,
      "step": 6
    },
    {
      "epoch": 0.004204835560895029,
      "grad_norm": 6.228534698486328,
      "learning_rate": 4.962019382530521e-05,
      "loss": 9.976,
      "step": 7
    },
    {
      "epoch": 0.004805526355308605,
      "grad_norm": 7.876675128936768,
      "learning_rate": 4.940740017799833e-05,
      "loss": 9.6633,
      "step": 8
    },
    {
      "epoch": 0.0054062171497221805,
      "grad_norm": 6.436480522155762,
      "learning_rate": 4.914814565722671e-05,
      "loss": 9.2801,
      "step": 9
    },
    {
      "epoch": 0.006006907944135756,
      "grad_norm": 5.75104284286499,
      "learning_rate": 4.884292376870567e-05,
      "loss": 8.7963,
      "step": 10
    },
    {
      "epoch": 0.006607598738549332,
      "grad_norm": 7.716401100158691,
      "learning_rate": 4.849231551964771e-05,
      "loss": 8.6959,
      "step": 11
    },
    {
      "epoch": 0.007208289532962907,
      "grad_norm": 6.399740219116211,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 8.1837,
      "step": 12
    },
    {
      "epoch": 0.007808980327376483,
      "grad_norm": 8.004280090332031,
      "learning_rate": 4.765769467591625e-05,
      "loss": 7.7803,
      "step": 13
    },
    {
      "epoch": 0.008409671121790058,
      "grad_norm": 6.805364608764648,
      "learning_rate": 4.717527082945554e-05,
      "loss": 8.1018,
      "step": 14
    },
    {
      "epoch": 0.009010361916203634,
      "grad_norm": 6.9764862060546875,
      "learning_rate": 4.665063509461097e-05,
      "loss": 7.4405,
      "step": 15
    },
    {
      "epoch": 0.00961105271061721,
      "grad_norm": 10.933174133300781,
      "learning_rate": 4.608478614532215e-05,
      "loss": 6.3451,
      "step": 16
    },
    {
      "epoch": 0.010211743505030785,
      "grad_norm": 7.365016937255859,
      "learning_rate": 4.54788011072248e-05,
      "loss": 5.6855,
      "step": 17
    },
    {
      "epoch": 0.010812434299444361,
      "grad_norm": 6.782474994659424,
      "learning_rate": 4.4833833507280884e-05,
      "loss": 5.1458,
      "step": 18
    },
    {
      "epoch": 0.011413125093857937,
      "grad_norm": 7.415083408355713,
      "learning_rate": 4.415111107797445e-05,
      "loss": 4.4723,
      "step": 19
    },
    {
      "epoch": 0.012013815888271513,
      "grad_norm": 6.618211269378662,
      "learning_rate": 4.34319334202531e-05,
      "loss": 4.4692,
      "step": 20
    },
    {
      "epoch": 0.012614506682685088,
      "grad_norm": 4.971122741699219,
      "learning_rate": 4.267766952966369e-05,
      "loss": 4.2879,
      "step": 21
    },
    {
      "epoch": 0.013215197477098664,
      "grad_norm": 5.271908760070801,
      "learning_rate": 4.188975519039151e-05,
      "loss": 4.3714,
      "step": 22
    },
    {
      "epoch": 0.01381588827151224,
      "grad_norm": 4.546558380126953,
      "learning_rate": 4.1069690242163484e-05,
      "loss": 4.7644,
      "step": 23
    },
    {
      "epoch": 0.014416579065925814,
      "grad_norm": 7.407399654388428,
      "learning_rate": 4.021903572521802e-05,
      "loss": 3.1589,
      "step": 24
    },
    {
      "epoch": 0.01501726986033939,
      "grad_norm": 5.464871406555176,
      "learning_rate": 3.933941090877615e-05,
      "loss": 3.7417,
      "step": 25
    },
    {
      "epoch": 0.01501726986033939,
      "eval_loss": 3.675921678543091,
      "eval_runtime": 72.7611,
      "eval_samples_per_second": 9.634,
      "eval_steps_per_second": 4.824,
      "step": 25
    },
    {
      "epoch": 0.015617960654752966,
      "grad_norm": 4.667582988739014,
      "learning_rate": 3.84324902086706e-05,
      "loss": 3.8327,
      "step": 26
    },
    {
      "epoch": 0.01621865144916654,
      "grad_norm": 4.277241230010986,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 3.5504,
      "step": 27
    },
    {
      "epoch": 0.016819342243580115,
      "grad_norm": 5.093675136566162,
      "learning_rate": 3.654371533087586e-05,
      "loss": 3.5189,
      "step": 28
    },
    {
      "epoch": 0.017420033037993693,
      "grad_norm": 5.327199459075928,
      "learning_rate": 3.556545654351749e-05,
      "loss": 3.3421,
      "step": 29
    },
    {
      "epoch": 0.018020723832407267,
      "grad_norm": 5.5413312911987305,
      "learning_rate": 3.456708580912725e-05,
      "loss": 2.9469,
      "step": 30
    },
    {
      "epoch": 0.018621414626820845,
      "grad_norm": 5.443083763122559,
      "learning_rate": 3.355050358314172e-05,
      "loss": 2.7866,
      "step": 31
    },
    {
      "epoch": 0.01922210542123442,
      "grad_norm": 5.232971668243408,
      "learning_rate": 3.251764498760683e-05,
      "loss": 3.3117,
      "step": 32
    },
    {
      "epoch": 0.019822796215647996,
      "grad_norm": 6.984073638916016,
      "learning_rate": 3.147047612756302e-05,
      "loss": 2.0666,
      "step": 33
    },
    {
      "epoch": 0.02042348701006157,
      "grad_norm": 6.457812309265137,
      "learning_rate": 3.0410990348452573e-05,
      "loss": 2.2777,
      "step": 34
    },
    {
      "epoch": 0.021024177804475148,
      "grad_norm": 6.987249374389648,
      "learning_rate": 2.9341204441673266e-05,
      "loss": 1.8346,
      "step": 35
    },
    {
      "epoch": 0.021624868598888722,
      "grad_norm": 6.425710201263428,
      "learning_rate": 2.8263154805501297e-05,
      "loss": 2.3781,
      "step": 36
    },
    {
      "epoch": 0.0222255593933023,
      "grad_norm": 6.388491630554199,
      "learning_rate": 2.717889356869146e-05,
      "loss": 1.7357,
      "step": 37
    },
    {
      "epoch": 0.022826250187715873,
      "grad_norm": 5.916223526000977,
      "learning_rate": 2.6090484684133404e-05,
      "loss": 1.5797,
      "step": 38
    },
    {
      "epoch": 0.023426940982129447,
      "grad_norm": 4.217414379119873,
      "learning_rate": 2.5e-05,
      "loss": 0.9489,
      "step": 39
    },
    {
      "epoch": 0.024027631776543025,
      "grad_norm": 5.929896354675293,
      "learning_rate": 2.3909515315866605e-05,
      "loss": 1.4266,
      "step": 40
    },
    {
      "epoch": 0.0246283225709566,
      "grad_norm": 6.1376519203186035,
      "learning_rate": 2.2821106431308544e-05,
      "loss": 1.6553,
      "step": 41
    },
    {
      "epoch": 0.025229013365370177,
      "grad_norm": 6.664175987243652,
      "learning_rate": 2.173684519449872e-05,
      "loss": 1.8489,
      "step": 42
    },
    {
      "epoch": 0.02582970415978375,
      "grad_norm": 4.3153462409973145,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 0.9044,
      "step": 43
    },
    {
      "epoch": 0.026430394954197328,
      "grad_norm": 5.153141021728516,
      "learning_rate": 1.958900965154743e-05,
      "loss": 1.0555,
      "step": 44
    },
    {
      "epoch": 0.027031085748610902,
      "grad_norm": 9.452554702758789,
      "learning_rate": 1.852952387243698e-05,
      "loss": 1.2836,
      "step": 45
    },
    {
      "epoch": 0.02763177654302448,
      "grad_norm": 4.951740264892578,
      "learning_rate": 1.7482355012393177e-05,
      "loss": 0.8965,
      "step": 46
    },
    {
      "epoch": 0.028232467337438054,
      "grad_norm": 5.227982997894287,
      "learning_rate": 1.6449496416858284e-05,
      "loss": 0.7981,
      "step": 47
    },
    {
      "epoch": 0.028833158131851628,
      "grad_norm": 2.884462356567383,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 0.3044,
      "step": 48
    },
    {
      "epoch": 0.029433848926265205,
      "grad_norm": 6.449427604675293,
      "learning_rate": 1.443454345648252e-05,
      "loss": 1.0199,
      "step": 49
    },
    {
      "epoch": 0.03003453972067878,
      "grad_norm": 5.113186836242676,
      "learning_rate": 1.3456284669124158e-05,
      "loss": 1.0111,
      "step": 50
    },
    {
      "epoch": 0.03003453972067878,
      "eval_loss": 0.9303993582725525,
      "eval_runtime": 72.6835,
      "eval_samples_per_second": 9.645,
      "eval_steps_per_second": 4.829,
      "step": 50
    },
    {
      "epoch": 0.030635230515092357,
      "grad_norm": 2.3707706928253174,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.1888,
      "step": 51
    },
    {
      "epoch": 0.03123592130950593,
      "grad_norm": 5.998414039611816,
      "learning_rate": 1.1567509791329401e-05,
      "loss": 1.524,
      "step": 52
    },
    {
      "epoch": 0.031836612103919505,
      "grad_norm": 5.471394062042236,
      "learning_rate": 1.0660589091223855e-05,
      "loss": 0.873,
      "step": 53
    },
    {
      "epoch": 0.03243730289833308,
      "grad_norm": 3.3917829990386963,
      "learning_rate": 9.780964274781984e-06,
      "loss": 0.2994,
      "step": 54
    },
    {
      "epoch": 0.03303799369274666,
      "grad_norm": 9.54757022857666,
      "learning_rate": 8.930309757836517e-06,
      "loss": 1.9844,
      "step": 55
    },
    {
      "epoch": 0.03363868448716023,
      "grad_norm": 8.63792896270752,
      "learning_rate": 8.110244809608495e-06,
      "loss": 1.3101,
      "step": 56
    },
    {
      "epoch": 0.03423937528157381,
      "grad_norm": 7.494466304779053,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 1.4655,
      "step": 57
    },
    {
      "epoch": 0.034840066075987386,
      "grad_norm": 8.181656837463379,
      "learning_rate": 6.568066579746901e-06,
      "loss": 1.1139,
      "step": 58
    },
    {
      "epoch": 0.03544075687040096,
      "grad_norm": 5.95154333114624,
      "learning_rate": 5.848888922025553e-06,
      "loss": 0.7435,
      "step": 59
    },
    {
      "epoch": 0.036041447664814534,
      "grad_norm": 5.259947299957275,
      "learning_rate": 5.166166492719124e-06,
      "loss": 0.2991,
      "step": 60
    },
    {
      "epoch": 0.03664213845922811,
      "grad_norm": 6.347657203674316,
      "learning_rate": 4.521198892775203e-06,
      "loss": 1.0288,
      "step": 61
    },
    {
      "epoch": 0.03724282925364169,
      "grad_norm": 17.088783264160156,
      "learning_rate": 3.9152138546778625e-06,
      "loss": 1.2506,
      "step": 62
    },
    {
      "epoch": 0.03784352004805527,
      "grad_norm": 18.076190948486328,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 0.8921,
      "step": 63
    },
    {
      "epoch": 0.03844421084246884,
      "grad_norm": 18.846956253051758,
      "learning_rate": 2.8247291705444575e-06,
      "loss": 0.656,
      "step": 64
    },
    {
      "epoch": 0.039044901636882415,
      "grad_norm": 12.805015563964844,
      "learning_rate": 2.3423053240837515e-06,
      "loss": 1.0612,
      "step": 65
    },
    {
      "epoch": 0.03964559243129599,
      "grad_norm": 15.975397109985352,
      "learning_rate": 1.9030116872178316e-06,
      "loss": 0.4972,
      "step": 66
    },
    {
      "epoch": 0.04024628322570956,
      "grad_norm": 6.866183757781982,
      "learning_rate": 1.5076844803522922e-06,
      "loss": 1.2505,
      "step": 67
    },
    {
      "epoch": 0.04084697402012314,
      "grad_norm": 7.4063849449157715,
      "learning_rate": 1.1570762312943295e-06,
      "loss": 1.6947,
      "step": 68
    },
    {
      "epoch": 0.04144766481453672,
      "grad_norm": 5.28386116027832,
      "learning_rate": 8.51854342773295e-07,
      "loss": 0.8198,
      "step": 69
    },
    {
      "epoch": 0.042048355608950296,
      "grad_norm": 6.2205376625061035,
      "learning_rate": 5.925998220016659e-07,
      "loss": 0.7195,
      "step": 70
    },
    {
      "epoch": 0.042649046403363866,
      "grad_norm": 3.0729503631591797,
      "learning_rate": 3.7980617469479953e-07,
      "loss": 0.15,
      "step": 71
    },
    {
      "epoch": 0.043249737197777444,
      "grad_norm": 4.537116050720215,
      "learning_rate": 2.1387846565474045e-07,
      "loss": 0.631,
      "step": 72
    },
    {
      "epoch": 0.04385042799219102,
      "grad_norm": 5.137740612030029,
      "learning_rate": 9.513254770636137e-08,
      "loss": 0.5103,
      "step": 73
    },
    {
      "epoch": 0.0444511187866046,
      "grad_norm": 7.137504577636719,
      "learning_rate": 2.3794460453555047e-08,
      "loss": 0.9672,
      "step": 74
    },
    {
      "epoch": 0.04505180958101817,
      "grad_norm": 6.272600173950195,
      "learning_rate": 0.0,
      "loss": 0.7572,
      "step": 75
    },
    {
      "epoch": 0.04505180958101817,
      "eval_loss": 0.7467929124832153,
      "eval_runtime": 72.7355,
      "eval_samples_per_second": 9.638,
      "eval_steps_per_second": 4.826,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.27255432331264e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}