{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09637393085170462,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00024093482712926153,
      "eval_loss": 5.2897210121154785,
      "eval_runtime": 52.997,
      "eval_samples_per_second": 131.894,
      "eval_steps_per_second": 16.492,
      "step": 1
    },
    {
      "epoch": 0.0012046741356463078,
      "grad_norm": 1.0848690271377563,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 5.2078,
      "step": 5
    },
    {
      "epoch": 0.0024093482712926155,
      "grad_norm": 0.9403343200683594,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 5.204,
      "step": 10
    },
    {
      "epoch": 0.003614022406938923,
      "grad_norm": 1.305862545967102,
      "learning_rate": 5e-05,
      "loss": 5.2467,
      "step": 15
    },
    {
      "epoch": 0.004818696542585231,
      "grad_norm": 1.322456955909729,
      "learning_rate": 6.666666666666667e-05,
      "loss": 4.9954,
      "step": 20
    },
    {
      "epoch": 0.006023370678231539,
      "grad_norm": 1.32424795627594,
      "learning_rate": 8.333333333333334e-05,
      "loss": 4.7048,
      "step": 25
    },
    {
      "epoch": 0.007228044813877846,
      "grad_norm": 1.7734204530715942,
      "learning_rate": 0.0001,
      "loss": 4.2781,
      "step": 30
    },
    {
      "epoch": 0.008432718949524154,
      "grad_norm": 1.6442747116088867,
      "learning_rate": 9.995494831023409e-05,
      "loss": 3.4232,
      "step": 35
    },
    {
      "epoch": 0.009637393085170462,
      "grad_norm": 1.4995731115341187,
      "learning_rate": 9.981987442712633e-05,
      "loss": 2.7847,
      "step": 40
    },
    {
      "epoch": 0.01084206722081677,
      "grad_norm": 1.3251590728759766,
      "learning_rate": 9.959502176294383e-05,
      "loss": 1.9015,
      "step": 45
    },
    {
      "epoch": 0.012046741356463078,
      "grad_norm": 1.3444932699203491,
      "learning_rate": 9.928079551738543e-05,
      "loss": 1.3271,
      "step": 50
    },
    {
      "epoch": 0.013251415492109385,
      "grad_norm": 1.079583764076233,
      "learning_rate": 9.887776194738432e-05,
      "loss": 0.8928,
      "step": 55
    },
    {
      "epoch": 0.014456089627755691,
      "grad_norm": 1.5913984775543213,
      "learning_rate": 9.838664734667495e-05,
      "loss": 0.6982,
      "step": 60
    },
    {
      "epoch": 0.015660763763402,
      "grad_norm": 1.5894569158554077,
      "learning_rate": 9.780833673696254e-05,
      "loss": 0.5173,
      "step": 65
    },
    {
      "epoch": 0.01686543789904831,
      "grad_norm": 1.1450620889663696,
      "learning_rate": 9.714387227305422e-05,
      "loss": 0.3779,
      "step": 70
    },
    {
      "epoch": 0.018070112034694615,
      "grad_norm": 1.1359564065933228,
      "learning_rate": 9.639445136482548e-05,
      "loss": 0.3262,
      "step": 75
    },
    {
      "epoch": 0.019274786170340924,
      "grad_norm": 1.096200942993164,
      "learning_rate": 9.55614245194068e-05,
      "loss": 0.313,
      "step": 80
    },
    {
      "epoch": 0.02047946030598723,
      "grad_norm": 1.1150457859039307,
      "learning_rate": 9.464629290747842e-05,
      "loss": 0.2924,
      "step": 85
    },
    {
      "epoch": 0.02168413444163354,
      "grad_norm": 0.9334543943405151,
      "learning_rate": 9.365070565805941e-05,
      "loss": 0.3151,
      "step": 90
    },
    {
      "epoch": 0.022888808577279846,
      "grad_norm": 1.1940410137176514,
      "learning_rate": 9.257645688666556e-05,
      "loss": 0.2857,
      "step": 95
    },
    {
      "epoch": 0.024093482712926155,
      "grad_norm": 0.8553321361541748,
      "learning_rate": 9.142548246219212e-05,
      "loss": 0.3003,
      "step": 100
    },
    {
      "epoch": 0.024093482712926155,
      "eval_loss": 0.3034798502922058,
      "eval_runtime": 53.3681,
      "eval_samples_per_second": 130.977,
      "eval_steps_per_second": 16.377,
      "step": 100
    },
    {
      "epoch": 0.02529815684857246,
      "grad_norm": 0.9065014719963074,
      "learning_rate": 9.019985651834703e-05,
      "loss": 0.312,
      "step": 105
    },
    {
      "epoch": 0.02650283098421877,
      "grad_norm": 0.6335747241973877,
      "learning_rate": 8.890178771592199e-05,
      "loss": 0.2791,
      "step": 110
    },
    {
      "epoch": 0.027707505119865077,
      "grad_norm": 0.6578128933906555,
      "learning_rate": 8.753361526263621e-05,
      "loss": 0.2982,
      "step": 115
    },
    {
      "epoch": 0.028912179255511383,
      "grad_norm": 0.7035508751869202,
      "learning_rate": 8.609780469772623e-05,
      "loss": 0.2783,
      "step": 120
    },
    {
      "epoch": 0.030116853391157692,
      "grad_norm": 0.6804089546203613,
      "learning_rate": 8.459694344887732e-05,
      "loss": 0.3074,
      "step": 125
    },
    {
      "epoch": 0.031321527526804,
      "grad_norm": 0.5222188830375671,
      "learning_rate": 8.303373616950408e-05,
      "loss": 0.2691,
      "step": 130
    },
    {
      "epoch": 0.03252620166245031,
      "grad_norm": 0.562334418296814,
      "learning_rate": 8.141099986478212e-05,
      "loss": 0.2822,
      "step": 135
    },
    {
      "epoch": 0.03373087579809662,
      "grad_norm": 0.60301274061203,
      "learning_rate": 7.973165881521434e-05,
      "loss": 0.31,
      "step": 140
    },
    {
      "epoch": 0.03493554993374292,
      "grad_norm": 0.6837559938430786,
      "learning_rate": 7.799873930687978e-05,
      "loss": 0.2665,
      "step": 145
    },
    {
      "epoch": 0.03614022406938923,
      "grad_norm": 0.8240361213684082,
      "learning_rate": 7.621536417786159e-05,
      "loss": 0.2911,
      "step": 150
    },
    {
      "epoch": 0.03734489820503554,
      "grad_norm": 0.6972349286079407,
      "learning_rate": 7.438474719068173e-05,
      "loss": 0.2831,
      "step": 155
    },
    {
      "epoch": 0.03854957234068185,
      "grad_norm": 0.5488475561141968,
      "learning_rate": 7.251018724088367e-05,
      "loss": 0.2925,
      "step": 160
    },
    {
      "epoch": 0.03975424647632815,
      "grad_norm": 0.4723394811153412,
      "learning_rate": 7.059506241219965e-05,
      "loss": 0.2756,
      "step": 165
    },
    {
      "epoch": 0.04095892061197446,
      "grad_norm": 0.679368793964386,
      "learning_rate": 6.864282388901544e-05,
      "loss": 0.2656,
      "step": 170
    },
    {
      "epoch": 0.04216359474762077,
      "grad_norm": 0.6478915214538574,
      "learning_rate": 6.665698973710288e-05,
      "loss": 0.2977,
      "step": 175
    },
    {
      "epoch": 0.04336826888326708,
      "grad_norm": 0.7039422988891602,
      "learning_rate": 6.464113856382752e-05,
      "loss": 0.2716,
      "step": 180
    },
    {
      "epoch": 0.04457294301891338,
      "grad_norm": 0.7704228162765503,
      "learning_rate": 6.259890306925627e-05,
      "loss": 0.2817,
      "step": 185
    },
    {
      "epoch": 0.04577761715455969,
      "grad_norm": 0.6130190491676331,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 0.2648,
      "step": 190
    },
    {
      "epoch": 0.046982291290206,
      "grad_norm": 0.7051613926887512,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 0.2755,
      "step": 195
    },
    {
      "epoch": 0.04818696542585231,
      "grad_norm": 0.517988920211792,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 0.2816,
      "step": 200
    },
    {
      "epoch": 0.04818696542585231,
      "eval_loss": 0.2893995940685272,
      "eval_runtime": 53.1802,
      "eval_samples_per_second": 131.44,
      "eval_steps_per_second": 16.435,
      "step": 200
    },
    {
      "epoch": 0.04939163956149861,
      "grad_norm": 0.6918057203292847,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 0.2937,
      "step": 205
    },
    {
      "epoch": 0.05059631369714492,
      "grad_norm": 0.8374642729759216,
      "learning_rate": 5.212206015980742e-05,
      "loss": 0.2727,
      "step": 210
    },
    {
      "epoch": 0.05180098783279123,
      "grad_norm": 0.49216243624687195,
      "learning_rate": 5e-05,
      "loss": 0.2739,
      "step": 215
    },
    {
      "epoch": 0.05300566196843754,
      "grad_norm": 0.6589741706848145,
      "learning_rate": 4.78779398401926e-05,
      "loss": 0.2759,
      "step": 220
    },
    {
      "epoch": 0.054210336104083844,
      "grad_norm": 0.4761958718299866,
      "learning_rate": 4.575970377622456e-05,
      "loss": 0.2809,
      "step": 225
    },
    {
      "epoch": 0.05541501023973015,
      "grad_norm": 0.37343281507492065,
      "learning_rate": 4.364910901265606e-05,
      "loss": 0.2614,
      "step": 230
    },
    {
      "epoch": 0.05661968437537646,
      "grad_norm": 0.5136386752128601,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 0.2538,
      "step": 235
    },
    {
      "epoch": 0.057824358511022765,
      "grad_norm": 0.5993496775627136,
      "learning_rate": 3.94660365002137e-05,
      "loss": 0.2833,
      "step": 240
    },
    {
      "epoch": 0.059029032646669075,
      "grad_norm": 0.47118353843688965,
      "learning_rate": 3.740109693074375e-05,
      "loss": 0.2765,
      "step": 245
    },
    {
      "epoch": 0.060233706782315384,
      "grad_norm": 0.39654070138931274,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 0.2778,
      "step": 250
    },
    {
      "epoch": 0.061438380917961694,
      "grad_norm": 0.4230641722679138,
      "learning_rate": 3.334301026289712e-05,
      "loss": 0.2804,
      "step": 255
    },
    {
      "epoch": 0.062643055053608,
      "grad_norm": 0.6153284311294556,
      "learning_rate": 3.135717611098458e-05,
      "loss": 0.2728,
      "step": 260
    },
    {
      "epoch": 0.06384772918925431,
      "grad_norm": 0.362914502620697,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 0.2678,
      "step": 265
    },
    {
      "epoch": 0.06505240332490062,
      "grad_norm": 0.4850432574748993,
      "learning_rate": 2.748981275911633e-05,
      "loss": 0.2645,
      "step": 270
    },
    {
      "epoch": 0.06625707746054692,
      "grad_norm": 0.5871238112449646,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 0.2548,
      "step": 275
    },
    {
      "epoch": 0.06746175159619323,
      "grad_norm": 0.5464058518409729,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 0.2674,
      "step": 280
    },
    {
      "epoch": 0.06866642573183954,
      "grad_norm": 0.6201205849647522,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 0.2812,
      "step": 285
    },
    {
      "epoch": 0.06987109986748584,
      "grad_norm": 0.3898628056049347,
      "learning_rate": 2.026834118478567e-05,
      "loss": 0.2747,
      "step": 290
    },
    {
      "epoch": 0.07107577400313216,
      "grad_norm": 0.5476693511009216,
      "learning_rate": 1.858900013521788e-05,
      "loss": 0.262,
      "step": 295
    },
    {
      "epoch": 0.07228044813877846,
      "grad_norm": 0.8837735056877136,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 0.2725,
      "step": 300
    },
    {
      "epoch": 0.07228044813877846,
      "eval_loss": 0.2828783392906189,
      "eval_runtime": 53.3466,
      "eval_samples_per_second": 131.03,
      "eval_steps_per_second": 16.383,
      "step": 300
    },
    {
      "epoch": 0.07348512227442477,
      "grad_norm": 0.6191293597221375,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 0.2534,
      "step": 305
    },
    {
      "epoch": 0.07468979641007108,
      "grad_norm": 0.5668566226959229,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 0.2605,
      "step": 310
    },
    {
      "epoch": 0.07589447054571738,
      "grad_norm": 0.7406247854232788,
      "learning_rate": 1.246638473736378e-05,
      "loss": 0.2719,
      "step": 315
    },
    {
      "epoch": 0.0770991446813637,
      "grad_norm": 0.4821166396141052,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 0.2556,
      "step": 320
    },
    {
      "epoch": 0.07830381881701,
      "grad_norm": 0.24732011556625366,
      "learning_rate": 9.800143481652979e-06,
      "loss": 0.2711,
      "step": 325
    },
    {
      "epoch": 0.0795084929526563,
      "grad_norm": 0.6188521385192871,
      "learning_rate": 8.574517537807897e-06,
      "loss": 0.2649,
      "step": 330
    },
    {
      "epoch": 0.08071316708830262,
      "grad_norm": 0.4498525857925415,
      "learning_rate": 7.423543113334436e-06,
      "loss": 0.2739,
      "step": 335
    },
    {
      "epoch": 0.08191784122394892,
      "grad_norm": 0.3962417244911194,
      "learning_rate": 6.349294341940593e-06,
      "loss": 0.2793,
      "step": 340
    },
    {
      "epoch": 0.08312251535959522,
      "grad_norm": 0.39472633600234985,
      "learning_rate": 5.353707092521582e-06,
      "loss": 0.2764,
      "step": 345
    },
    {
      "epoch": 0.08432718949524154,
      "grad_norm": 0.39465591311454773,
      "learning_rate": 4.43857548059321e-06,
      "loss": 0.2761,
      "step": 350
    },
    {
      "epoch": 0.08553186363088784,
      "grad_norm": 0.44090038537979126,
      "learning_rate": 3.605548635174533e-06,
      "loss": 0.2781,
      "step": 355
    },
    {
      "epoch": 0.08673653776653416,
      "grad_norm": 0.5822060108184814,
      "learning_rate": 2.85612772694579e-06,
      "loss": 0.2697,
      "step": 360
    },
    {
      "epoch": 0.08794121190218046,
      "grad_norm": 0.41576147079467773,
      "learning_rate": 2.191663263037458e-06,
      "loss": 0.2655,
      "step": 365
    },
    {
      "epoch": 0.08914588603782676,
      "grad_norm": 0.4551864564418793,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 0.26,
      "step": 370
    },
    {
      "epoch": 0.09035056017347308,
      "grad_norm": 0.6066895127296448,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 0.2755,
      "step": 375
    },
    {
      "epoch": 0.09155523430911938,
      "grad_norm": 0.7577335238456726,
      "learning_rate": 7.192044826145771e-07,
      "loss": 0.2671,
      "step": 380
    },
    {
      "epoch": 0.09275990844476568,
      "grad_norm": 0.6159568428993225,
      "learning_rate": 4.049782370561583e-07,
      "loss": 0.2654,
      "step": 385
    },
    {
      "epoch": 0.093964582580412,
      "grad_norm": 0.32610562443733215,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 0.2714,
      "step": 390
    },
    {
      "epoch": 0.0951692567160583,
      "grad_norm": 0.5694824457168579,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 0.2673,
      "step": 395
    },
    {
      "epoch": 0.09637393085170462,
      "grad_norm": 0.6154575347900391,
      "learning_rate": 0.0,
      "loss": 0.2692,
      "step": 400
    },
    {
      "epoch": 0.09637393085170462,
      "eval_loss": 0.2801929712295532,
      "eval_runtime": 53.5151,
      "eval_samples_per_second": 130.617,
      "eval_steps_per_second": 16.332,
      "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": 1.2815911801480806e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}