{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14450867052023122,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000361271676300578,
      "eval_loss": 1.744890570640564,
      "eval_runtime": 94.7563,
      "eval_samples_per_second": 12.305,
      "eval_steps_per_second": 6.153,
      "step": 1
    },
    {
      "epoch": 0.0018063583815028901,
      "grad_norm": 4.527747631072998,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 6.4698,
      "step": 5
    },
    {
      "epoch": 0.0036127167630057803,
      "grad_norm": 5.123751640319824,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 5.8106,
      "step": 10
    },
    {
      "epoch": 0.00541907514450867,
      "grad_norm": 6.700563430786133,
      "learning_rate": 5e-05,
      "loss": 6.232,
      "step": 15
    },
    {
      "epoch": 0.0072254335260115606,
      "grad_norm": 5.669617652893066,
      "learning_rate": 6.666666666666667e-05,
      "loss": 6.5045,
      "step": 20
    },
    {
      "epoch": 0.009031791907514452,
      "grad_norm": 6.724331855773926,
      "learning_rate": 8.333333333333334e-05,
      "loss": 6.1928,
      "step": 25
    },
    {
      "epoch": 0.01083815028901734,
      "grad_norm": 7.525301456451416,
      "learning_rate": 0.0001,
      "loss": 6.8691,
      "step": 30
    },
    {
      "epoch": 0.012644508670520232,
      "grad_norm": 7.290944576263428,
      "learning_rate": 9.995494831023409e-05,
      "loss": 5.8447,
      "step": 35
    },
    {
      "epoch": 0.014450867052023121,
      "grad_norm": 10.550713539123535,
      "learning_rate": 9.981987442712633e-05,
      "loss": 6.6429,
      "step": 40
    },
    {
      "epoch": 0.01625722543352601,
      "grad_norm": 10.511975288391113,
      "learning_rate": 9.959502176294383e-05,
      "loss": 6.1337,
      "step": 45
    },
    {
      "epoch": 0.018063583815028903,
      "grad_norm": 21.367212295532227,
      "learning_rate": 9.928079551738543e-05,
      "loss": 6.4784,
      "step": 50
    },
    {
      "epoch": 0.019869942196531792,
      "grad_norm": 4.25766658782959,
      "learning_rate": 9.887776194738432e-05,
      "loss": 5.6619,
      "step": 55
    },
    {
      "epoch": 0.02167630057803468,
      "grad_norm": 3.647825241088867,
      "learning_rate": 9.838664734667495e-05,
      "loss": 5.6285,
      "step": 60
    },
    {
      "epoch": 0.02348265895953757,
      "grad_norm": 4.4724931716918945,
      "learning_rate": 9.780833673696254e-05,
      "loss": 5.9513,
      "step": 65
    },
    {
      "epoch": 0.025289017341040464,
      "grad_norm": 4.866231918334961,
      "learning_rate": 9.714387227305422e-05,
      "loss": 6.3579,
      "step": 70
    },
    {
      "epoch": 0.027095375722543353,
      "grad_norm": 5.625385761260986,
      "learning_rate": 9.639445136482548e-05,
      "loss": 6.4269,
      "step": 75
    },
    {
      "epoch": 0.028901734104046242,
      "grad_norm": 7.687127113342285,
      "learning_rate": 9.55614245194068e-05,
      "loss": 5.9336,
      "step": 80
    },
    {
      "epoch": 0.03070809248554913,
      "grad_norm": 6.402472496032715,
      "learning_rate": 9.464629290747842e-05,
      "loss": 6.1318,
      "step": 85
    },
    {
      "epoch": 0.03251445086705202,
      "grad_norm": 7.3071722984313965,
      "learning_rate": 9.365070565805941e-05,
      "loss": 6.607,
      "step": 90
    },
    {
      "epoch": 0.034320809248554913,
      "grad_norm": 9.246926307678223,
      "learning_rate": 9.257645688666556e-05,
      "loss": 6.4302,
      "step": 95
    },
    {
      "epoch": 0.036127167630057806,
      "grad_norm": 22.087501525878906,
      "learning_rate": 9.142548246219212e-05,
      "loss": 6.5766,
      "step": 100
    },
    {
      "epoch": 0.036127167630057806,
      "eval_loss": 1.544723391532898,
      "eval_runtime": 96.2658,
      "eval_samples_per_second": 12.112,
      "eval_steps_per_second": 6.056,
      "step": 100
    },
    {
      "epoch": 0.03793352601156069,
      "grad_norm": 4.280524253845215,
      "learning_rate": 9.019985651834703e-05,
      "loss": 5.4429,
      "step": 105
    },
    {
      "epoch": 0.039739884393063585,
      "grad_norm": 3.746527671813965,
      "learning_rate": 8.890178771592199e-05,
      "loss": 5.9457,
      "step": 110
    },
    {
      "epoch": 0.04154624277456647,
      "grad_norm": 3.7925260066986084,
      "learning_rate": 8.753361526263621e-05,
      "loss": 5.8436,
      "step": 115
    },
    {
      "epoch": 0.04335260115606936,
      "grad_norm": 5.027681827545166,
      "learning_rate": 8.609780469772623e-05,
      "loss": 6.661,
      "step": 120
    },
    {
      "epoch": 0.045158959537572256,
      "grad_norm": 6.989440441131592,
      "learning_rate": 8.459694344887732e-05,
      "loss": 5.4947,
      "step": 125
    },
    {
      "epoch": 0.04696531791907514,
      "grad_norm": 5.413540840148926,
      "learning_rate": 8.303373616950408e-05,
      "loss": 5.849,
      "step": 130
    },
    {
      "epoch": 0.048771676300578035,
      "grad_norm": 7.488022804260254,
      "learning_rate": 8.141099986478212e-05,
      "loss": 6.7765,
      "step": 135
    },
    {
      "epoch": 0.05057803468208093,
      "grad_norm": 6.465548038482666,
      "learning_rate": 7.973165881521434e-05,
      "loss": 6.3102,
      "step": 140
    },
    {
      "epoch": 0.05238439306358381,
      "grad_norm": 8.735454559326172,
      "learning_rate": 7.799873930687978e-05,
      "loss": 5.7564,
      "step": 145
    },
    {
      "epoch": 0.054190751445086706,
      "grad_norm": 16.286537170410156,
      "learning_rate": 7.621536417786159e-05,
      "loss": 6.5821,
      "step": 150
    },
    {
      "epoch": 0.0559971098265896,
      "grad_norm": 3.690650224685669,
      "learning_rate": 7.438474719068173e-05,
      "loss": 5.8175,
      "step": 155
    },
    {
      "epoch": 0.057803468208092484,
      "grad_norm": 3.5886545181274414,
      "learning_rate": 7.251018724088367e-05,
      "loss": 5.7625,
      "step": 160
    },
    {
      "epoch": 0.05960982658959538,
      "grad_norm": 4.576591968536377,
      "learning_rate": 7.059506241219965e-05,
      "loss": 5.8882,
      "step": 165
    },
    {
      "epoch": 0.06141618497109826,
      "grad_norm": 5.132069110870361,
      "learning_rate": 6.864282388901544e-05,
      "loss": 5.7749,
      "step": 170
    },
    {
      "epoch": 0.06322254335260116,
      "grad_norm": 6.244584560394287,
      "learning_rate": 6.665698973710288e-05,
      "loss": 5.5289,
      "step": 175
    },
    {
      "epoch": 0.06502890173410404,
      "grad_norm": 5.539905548095703,
      "learning_rate": 6.464113856382752e-05,
      "loss": 6.0146,
      "step": 180
    },
    {
      "epoch": 0.06683526011560693,
      "grad_norm": 5.4433417320251465,
      "learning_rate": 6.259890306925627e-05,
      "loss": 5.4645,
      "step": 185
    },
    {
      "epoch": 0.06864161849710983,
      "grad_norm": 7.424625873565674,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 5.9284,
      "step": 190
    },
    {
      "epoch": 0.07044797687861272,
      "grad_norm": 10.676475524902344,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 6.3977,
      "step": 195
    },
    {
      "epoch": 0.07225433526011561,
      "grad_norm": 16.99396514892578,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 7.3271,
      "step": 200
    },
    {
      "epoch": 0.07225433526011561,
      "eval_loss": 1.511218547821045,
      "eval_runtime": 95.9396,
      "eval_samples_per_second": 12.153,
      "eval_steps_per_second": 6.077,
      "step": 200
    },
    {
      "epoch": 0.07406069364161849,
      "grad_norm": 3.2789666652679443,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 5.5143,
      "step": 205
    },
    {
      "epoch": 0.07586705202312138,
      "grad_norm": 3.9596450328826904,
      "learning_rate": 5.212206015980742e-05,
      "loss": 6.0861,
      "step": 210
    },
    {
      "epoch": 0.07767341040462428,
      "grad_norm": 3.611206293106079,
      "learning_rate": 5e-05,
      "loss": 6.0573,
      "step": 215
    },
    {
      "epoch": 0.07947976878612717,
      "grad_norm": 5.087730407714844,
      "learning_rate": 4.78779398401926e-05,
      "loss": 5.8048,
      "step": 220
    },
    {
      "epoch": 0.08128612716763006,
      "grad_norm": 6.118533611297607,
      "learning_rate": 4.575970377622456e-05,
      "loss": 5.8367,
      "step": 225
    },
    {
      "epoch": 0.08309248554913294,
      "grad_norm": 6.310227870941162,
      "learning_rate": 4.364910901265606e-05,
      "loss": 5.8543,
      "step": 230
    },
    {
      "epoch": 0.08489884393063583,
      "grad_norm": 6.936134338378906,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 5.796,
      "step": 235
    },
    {
      "epoch": 0.08670520231213873,
      "grad_norm": 8.067972183227539,
      "learning_rate": 3.94660365002137e-05,
      "loss": 6.3736,
      "step": 240
    },
    {
      "epoch": 0.08851156069364162,
      "grad_norm": 7.617551803588867,
      "learning_rate": 3.740109693074375e-05,
      "loss": 5.934,
      "step": 245
    },
    {
      "epoch": 0.09031791907514451,
      "grad_norm": 13.973454475402832,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 6.4798,
      "step": 250
    },
    {
      "epoch": 0.0921242774566474,
      "grad_norm": 2.9241528511047363,
      "learning_rate": 3.334301026289712e-05,
      "loss": 5.8853,
      "step": 255
    },
    {
      "epoch": 0.09393063583815028,
      "grad_norm": 3.5740983486175537,
      "learning_rate": 3.135717611098458e-05,
      "loss": 5.6328,
      "step": 260
    },
    {
      "epoch": 0.09573699421965318,
      "grad_norm": 3.7815191745758057,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 5.6854,
      "step": 265
    },
    {
      "epoch": 0.09754335260115607,
      "grad_norm": 4.931917190551758,
      "learning_rate": 2.748981275911633e-05,
      "loss": 5.1757,
      "step": 270
    },
    {
      "epoch": 0.09934971098265896,
      "grad_norm": 5.226539134979248,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 5.5276,
      "step": 275
    },
    {
      "epoch": 0.10115606936416185,
      "grad_norm": 5.994261264801025,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 5.7058,
      "step": 280
    },
    {
      "epoch": 0.10296242774566473,
      "grad_norm": 7.569850444793701,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 6.4142,
      "step": 285
    },
    {
      "epoch": 0.10476878612716763,
      "grad_norm": 8.362022399902344,
      "learning_rate": 2.026834118478567e-05,
      "loss": 5.561,
      "step": 290
    },
    {
      "epoch": 0.10657514450867052,
      "grad_norm": 7.891885280609131,
      "learning_rate": 1.858900013521788e-05,
      "loss": 5.7983,
      "step": 295
    },
    {
      "epoch": 0.10838150289017341,
      "grad_norm": 21.714279174804688,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 6.4295,
      "step": 300
    },
    {
      "epoch": 0.10838150289017341,
      "eval_loss": 1.5002806186676025,
      "eval_runtime": 96.082,
      "eval_samples_per_second": 12.135,
      "eval_steps_per_second": 6.068,
      "step": 300
    },
    {
      "epoch": 0.1101878612716763,
      "grad_norm": 3.084392786026001,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 5.1598,
      "step": 305
    },
    {
      "epoch": 0.1119942196531792,
      "grad_norm": 3.4714620113372803,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 5.8816,
      "step": 310
    },
    {
      "epoch": 0.11380057803468208,
      "grad_norm": 3.8589141368865967,
      "learning_rate": 1.246638473736378e-05,
      "loss": 6.0373,
      "step": 315
    },
    {
      "epoch": 0.11560693641618497,
      "grad_norm": 5.173672199249268,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 6.076,
      "step": 320
    },
    {
      "epoch": 0.11741329479768786,
      "grad_norm": 4.328430652618408,
      "learning_rate": 9.800143481652979e-06,
      "loss": 6.304,
      "step": 325
    },
    {
      "epoch": 0.11921965317919075,
      "grad_norm": 5.293956756591797,
      "learning_rate": 8.574517537807897e-06,
      "loss": 5.7655,
      "step": 330
    },
    {
      "epoch": 0.12102601156069365,
      "grad_norm": 5.817462921142578,
      "learning_rate": 7.423543113334436e-06,
      "loss": 6.1302,
      "step": 335
    },
    {
      "epoch": 0.12283236994219653,
      "grad_norm": 6.929890155792236,
      "learning_rate": 6.349294341940593e-06,
      "loss": 6.7549,
      "step": 340
    },
    {
      "epoch": 0.12463872832369942,
      "grad_norm": 7.3396806716918945,
      "learning_rate": 5.353707092521582e-06,
      "loss": 5.9364,
      "step": 345
    },
    {
      "epoch": 0.12644508670520233,
      "grad_norm": 21.20209312438965,
      "learning_rate": 4.43857548059321e-06,
      "loss": 5.9477,
      "step": 350
    },
    {
      "epoch": 0.1282514450867052,
      "grad_norm": 3.2652978897094727,
      "learning_rate": 3.605548635174533e-06,
      "loss": 5.5227,
      "step": 355
    },
    {
      "epoch": 0.13005780346820808,
      "grad_norm": 3.4103219509124756,
      "learning_rate": 2.85612772694579e-06,
      "loss": 5.9119,
      "step": 360
    },
    {
      "epoch": 0.13186416184971098,
      "grad_norm": 3.565873384475708,
      "learning_rate": 2.191663263037458e-06,
      "loss": 5.5844,
      "step": 365
    },
    {
      "epoch": 0.13367052023121387,
      "grad_norm": 4.700222492218018,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 6.0105,
      "step": 370
    },
    {
      "epoch": 0.13547687861271676,
      "grad_norm": 6.093208312988281,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 5.7714,
      "step": 375
    },
    {
      "epoch": 0.13728323699421965,
      "grad_norm": 6.380523204803467,
      "learning_rate": 7.192044826145771e-07,
      "loss": 5.7834,
      "step": 380
    },
    {
      "epoch": 0.13908959537572255,
      "grad_norm": 5.724410057067871,
      "learning_rate": 4.049782370561583e-07,
      "loss": 6.0206,
      "step": 385
    },
    {
      "epoch": 0.14089595375722544,
      "grad_norm": 5.523743629455566,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 5.5813,
      "step": 390
    },
    {
      "epoch": 0.14270231213872833,
      "grad_norm": 7.912516117095947,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 6.2944,
      "step": 395
    },
    {
      "epoch": 0.14450867052023122,
      "grad_norm": 12.813782691955566,
      "learning_rate": 0.0,
      "loss": 6.3883,
      "step": 400
    },
    {
      "epoch": 0.14450867052023122,
      "eval_loss": 1.4948960542678833,
      "eval_runtime": 96.2109,
      "eval_samples_per_second": 12.119,
      "eval_steps_per_second": 6.06,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 400,
  "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": 1.4301801881586893e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}