{
  "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": 53.1461,
      "eval_samples_per_second": 131.524,
      "eval_steps_per_second": 16.445,
      "step": 1
    },
    {
      "epoch": 0.0012046741356463078,
      "grad_norm": 1.0046111345291138,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 5.2064,
      "step": 5
    },
    {
      "epoch": 0.0024093482712926155,
      "grad_norm": 0.8802908062934875,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 5.2079,
      "step": 10
    },
    {
      "epoch": 0.003614022406938923,
      "grad_norm": 1.2555723190307617,
      "learning_rate": 5e-05,
      "loss": 5.2505,
      "step": 15
    },
    {
      "epoch": 0.004818696542585231,
      "grad_norm": 1.2714437246322632,
      "learning_rate": 6.666666666666667e-05,
      "loss": 5.0022,
      "step": 20
    },
    {
      "epoch": 0.006023370678231539,
      "grad_norm": 1.2646763324737549,
      "learning_rate": 8.333333333333334e-05,
      "loss": 4.713,
      "step": 25
    },
    {
      "epoch": 0.007228044813877846,
      "grad_norm": 1.7209545373916626,
      "learning_rate": 0.0001,
      "loss": 4.2882,
      "step": 30
    },
    {
      "epoch": 0.008432718949524154,
      "grad_norm": 1.609715223312378,
      "learning_rate": 9.995494831023409e-05,
      "loss": 3.436,
      "step": 35
    },
    {
      "epoch": 0.009637393085170462,
      "grad_norm": 1.493584394454956,
      "learning_rate": 9.981987442712633e-05,
      "loss": 2.7986,
      "step": 40
    },
    {
      "epoch": 0.01084206722081677,
      "grad_norm": 1.3131476640701294,
      "learning_rate": 9.959502176294383e-05,
      "loss": 1.9188,
      "step": 45
    },
    {
      "epoch": 0.012046741356463078,
      "grad_norm": 1.3303972482681274,
      "learning_rate": 9.928079551738543e-05,
      "loss": 1.3451,
      "step": 50
    },
    {
      "epoch": 0.013251415492109385,
      "grad_norm": 1.0859252214431763,
      "learning_rate": 9.887776194738432e-05,
      "loss": 0.9085,
      "step": 55
    },
    {
      "epoch": 0.014456089627755691,
      "grad_norm": 1.555842638015747,
      "learning_rate": 9.838664734667495e-05,
      "loss": 0.7073,
      "step": 60
    },
    {
      "epoch": 0.015660763763402,
      "grad_norm": 1.5463906526565552,
      "learning_rate": 9.780833673696254e-05,
      "loss": 0.5272,
      "step": 65
    },
    {
      "epoch": 0.01686543789904831,
      "grad_norm": 1.1626412868499756,
      "learning_rate": 9.714387227305422e-05,
      "loss": 0.3814,
      "step": 70
    },
    {
      "epoch": 0.018070112034694615,
      "grad_norm": 1.0962865352630615,
      "learning_rate": 9.639445136482548e-05,
      "loss": 0.3307,
      "step": 75
    },
    {
      "epoch": 0.019274786170340924,
      "grad_norm": 1.046875238418579,
      "learning_rate": 9.55614245194068e-05,
      "loss": 0.3167,
      "step": 80
    },
    {
      "epoch": 0.02047946030598723,
      "grad_norm": 1.041786789894104,
      "learning_rate": 9.464629290747842e-05,
      "loss": 0.291,
      "step": 85
    },
    {
      "epoch": 0.02168413444163354,
      "grad_norm": 0.9495665431022644,
      "learning_rate": 9.365070565805941e-05,
      "loss": 0.3142,
      "step": 90
    },
    {
      "epoch": 0.022888808577279846,
      "grad_norm": 1.2442537546157837,
      "learning_rate": 9.257645688666556e-05,
      "loss": 0.2832,
      "step": 95
    },
    {
      "epoch": 0.024093482712926155,
      "grad_norm": 0.8132896423339844,
      "learning_rate": 9.142548246219212e-05,
      "loss": 0.2985,
      "step": 100
    },
    {
      "epoch": 0.024093482712926155,
      "eval_loss": 0.30343782901763916,
      "eval_runtime": 53.1552,
      "eval_samples_per_second": 131.502,
      "eval_steps_per_second": 16.442,
      "step": 100
    },
    {
      "epoch": 0.02529815684857246,
      "grad_norm": 0.8665286898612976,
      "learning_rate": 9.019985651834703e-05,
      "loss": 0.3103,
      "step": 105
    },
    {
      "epoch": 0.02650283098421877,
      "grad_norm": 0.6252511143684387,
      "learning_rate": 8.890178771592199e-05,
      "loss": 0.2804,
      "step": 110
    },
    {
      "epoch": 0.027707505119865077,
      "grad_norm": 0.6132208704948425,
      "learning_rate": 8.753361526263621e-05,
      "loss": 0.2967,
      "step": 115
    },
    {
      "epoch": 0.028912179255511383,
      "grad_norm": 0.73247891664505,
      "learning_rate": 8.609780469772623e-05,
      "loss": 0.278,
      "step": 120
    },
    {
      "epoch": 0.030116853391157692,
      "grad_norm": 0.68526291847229,
      "learning_rate": 8.459694344887732e-05,
      "loss": 0.3071,
      "step": 125
    },
    {
      "epoch": 0.031321527526804,
      "grad_norm": 0.5240058302879333,
      "learning_rate": 8.303373616950408e-05,
      "loss": 0.2684,
      "step": 130
    },
    {
      "epoch": 0.03252620166245031,
      "grad_norm": 0.6084133982658386,
      "learning_rate": 8.141099986478212e-05,
      "loss": 0.2803,
      "step": 135
    },
    {
      "epoch": 0.03373087579809662,
      "grad_norm": 0.5869400501251221,
      "learning_rate": 7.973165881521434e-05,
      "loss": 0.3084,
      "step": 140
    },
    {
      "epoch": 0.03493554993374292,
      "grad_norm": 0.7005964517593384,
      "learning_rate": 7.799873930687978e-05,
      "loss": 0.2686,
      "step": 145
    },
    {
      "epoch": 0.03614022406938923,
      "grad_norm": 0.8660863637924194,
      "learning_rate": 7.621536417786159e-05,
      "loss": 0.291,
      "step": 150
    },
    {
      "epoch": 0.03734489820503554,
      "grad_norm": 0.7054917216300964,
      "learning_rate": 7.438474719068173e-05,
      "loss": 0.2843,
      "step": 155
    },
    {
      "epoch": 0.03854957234068185,
      "grad_norm": 0.5891161561012268,
      "learning_rate": 7.251018724088367e-05,
      "loss": 0.2955,
      "step": 160
    },
    {
      "epoch": 0.03975424647632815,
      "grad_norm": 0.5015525817871094,
      "learning_rate": 7.059506241219965e-05,
      "loss": 0.2759,
      "step": 165
    },
    {
      "epoch": 0.04095892061197446,
      "grad_norm": 0.6801341772079468,
      "learning_rate": 6.864282388901544e-05,
      "loss": 0.2661,
      "step": 170
    },
    {
      "epoch": 0.04216359474762077,
      "grad_norm": 0.6425898671150208,
      "learning_rate": 6.665698973710288e-05,
      "loss": 0.2973,
      "step": 175
    },
    {
      "epoch": 0.04336826888326708,
      "grad_norm": 0.6975763440132141,
      "learning_rate": 6.464113856382752e-05,
      "loss": 0.2702,
      "step": 180
    },
    {
      "epoch": 0.04457294301891338,
      "grad_norm": 0.766609787940979,
      "learning_rate": 6.259890306925627e-05,
      "loss": 0.2814,
      "step": 185
    },
    {
      "epoch": 0.04577761715455969,
      "grad_norm": 0.6040458679199219,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 0.2651,
      "step": 190
    },
    {
      "epoch": 0.046982291290206,
      "grad_norm": 0.7015875577926636,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 0.2746,
      "step": 195
    },
    {
      "epoch": 0.04818696542585231,
      "grad_norm": 0.5288679003715515,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 0.2817,
      "step": 200
    },
    {
      "epoch": 0.04818696542585231,
      "eval_loss": 0.28946301341056824,
      "eval_runtime": 53.284,
      "eval_samples_per_second": 131.184,
      "eval_steps_per_second": 16.403,
      "step": 200
    },
    {
      "epoch": 0.04939163956149861,
      "grad_norm": 0.6936432123184204,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 0.2937,
      "step": 205
    },
    {
      "epoch": 0.05059631369714492,
      "grad_norm": 0.8455679416656494,
      "learning_rate": 5.212206015980742e-05,
      "loss": 0.272,
      "step": 210
    },
    {
      "epoch": 0.05180098783279123,
      "grad_norm": 0.49571552872657776,
      "learning_rate": 5e-05,
      "loss": 0.2751,
      "step": 215
    },
    {
      "epoch": 0.05300566196843754,
      "grad_norm": 0.6435004472732544,
      "learning_rate": 4.78779398401926e-05,
      "loss": 0.2768,
      "step": 220
    },
    {
      "epoch": 0.054210336104083844,
      "grad_norm": 0.48980122804641724,
      "learning_rate": 4.575970377622456e-05,
      "loss": 0.2808,
      "step": 225
    },
    {
      "epoch": 0.05541501023973015,
      "grad_norm": 0.38407304883003235,
      "learning_rate": 4.364910901265606e-05,
      "loss": 0.2616,
      "step": 230
    },
    {
      "epoch": 0.05661968437537646,
      "grad_norm": 0.5096237659454346,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 0.2537,
      "step": 235
    },
    {
      "epoch": 0.057824358511022765,
      "grad_norm": 0.6108520030975342,
      "learning_rate": 3.94660365002137e-05,
      "loss": 0.2835,
      "step": 240
    },
    {
      "epoch": 0.059029032646669075,
      "grad_norm": 0.4757826328277588,
      "learning_rate": 3.740109693074375e-05,
      "loss": 0.2761,
      "step": 245
    },
    {
      "epoch": 0.060233706782315384,
      "grad_norm": 0.4005926549434662,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 0.2775,
      "step": 250
    },
    {
      "epoch": 0.061438380917961694,
      "grad_norm": 0.4221913516521454,
      "learning_rate": 3.334301026289712e-05,
      "loss": 0.2805,
      "step": 255
    },
    {
      "epoch": 0.062643055053608,
      "grad_norm": 0.6178380250930786,
      "learning_rate": 3.135717611098458e-05,
      "loss": 0.2728,
      "step": 260
    },
    {
      "epoch": 0.06384772918925431,
      "grad_norm": 0.362184077501297,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 0.2676,
      "step": 265
    },
    {
      "epoch": 0.06505240332490062,
      "grad_norm": 0.47867563366889954,
      "learning_rate": 2.748981275911633e-05,
      "loss": 0.2643,
      "step": 270
    },
    {
      "epoch": 0.06625707746054692,
      "grad_norm": 0.587843656539917,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 0.2562,
      "step": 275
    },
    {
      "epoch": 0.06746175159619323,
      "grad_norm": 0.5621172785758972,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 0.2679,
      "step": 280
    },
    {
      "epoch": 0.06866642573183954,
      "grad_norm": 0.6250373125076294,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 0.2809,
      "step": 285
    },
    {
      "epoch": 0.06987109986748584,
      "grad_norm": 0.3908781409263611,
      "learning_rate": 2.026834118478567e-05,
      "loss": 0.2745,
      "step": 290
    },
    {
      "epoch": 0.07107577400313216,
      "grad_norm": 0.5624713897705078,
      "learning_rate": 1.858900013521788e-05,
      "loss": 0.2631,
      "step": 295
    },
    {
      "epoch": 0.07228044813877846,
      "grad_norm": 0.9051156044006348,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 0.2721,
      "step": 300
    },
    {
      "epoch": 0.07228044813877846,
      "eval_loss": 0.2828942537307739,
      "eval_runtime": 53.296,
      "eval_samples_per_second": 131.154,
      "eval_steps_per_second": 16.399,
      "step": 300
    },
    {
      "epoch": 0.07348512227442477,
      "grad_norm": 0.6152680516242981,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 0.2531,
      "step": 305
    },
    {
      "epoch": 0.07468979641007108,
      "grad_norm": 0.5890482664108276,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 0.2609,
      "step": 310
    },
    {
      "epoch": 0.07589447054571738,
      "grad_norm": 0.7539456486701965,
      "learning_rate": 1.246638473736378e-05,
      "loss": 0.2714,
      "step": 315
    },
    {
      "epoch": 0.0770991446813637,
      "grad_norm": 0.49839717149734497,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 0.2566,
      "step": 320
    },
    {
      "epoch": 0.07830381881701,
      "grad_norm": 0.24684111773967743,
      "learning_rate": 9.800143481652979e-06,
      "loss": 0.2706,
      "step": 325
    },
    {
      "epoch": 0.0795084929526563,
      "grad_norm": 0.6296346783638,
      "learning_rate": 8.574517537807897e-06,
      "loss": 0.265,
      "step": 330
    },
    {
      "epoch": 0.08071316708830262,
      "grad_norm": 0.44885319471359253,
      "learning_rate": 7.423543113334436e-06,
      "loss": 0.2728,
      "step": 335
    },
    {
      "epoch": 0.08191784122394892,
      "grad_norm": 0.40835171937942505,
      "learning_rate": 6.349294341940593e-06,
      "loss": 0.2799,
      "step": 340
    },
    {
      "epoch": 0.08312251535959522,
      "grad_norm": 0.40302494168281555,
      "learning_rate": 5.353707092521582e-06,
      "loss": 0.2759,
      "step": 345
    },
    {
      "epoch": 0.08432718949524154,
      "grad_norm": 0.39175310730934143,
      "learning_rate": 4.43857548059321e-06,
      "loss": 0.2762,
      "step": 350
    },
    {
      "epoch": 0.08553186363088784,
      "grad_norm": 0.44972530007362366,
      "learning_rate": 3.605548635174533e-06,
      "loss": 0.2786,
      "step": 355
    },
    {
      "epoch": 0.08673653776653416,
      "grad_norm": 0.5868881344795227,
      "learning_rate": 2.85612772694579e-06,
      "loss": 0.2697,
      "step": 360
    },
    {
      "epoch": 0.08794121190218046,
      "grad_norm": 0.41870003938674927,
      "learning_rate": 2.191663263037458e-06,
      "loss": 0.2653,
      "step": 365
    },
    {
      "epoch": 0.08914588603782676,
      "grad_norm": 0.46780121326446533,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 0.2588,
      "step": 370
    },
    {
      "epoch": 0.09035056017347308,
      "grad_norm": 0.617438554763794,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 0.276,
      "step": 375
    },
    {
      "epoch": 0.09155523430911938,
      "grad_norm": 0.7706754803657532,
      "learning_rate": 7.192044826145771e-07,
      "loss": 0.2673,
      "step": 380
    },
    {
      "epoch": 0.09275990844476568,
      "grad_norm": 0.6125733256340027,
      "learning_rate": 4.049782370561583e-07,
      "loss": 0.2647,
      "step": 385
    },
    {
      "epoch": 0.093964582580412,
      "grad_norm": 0.3331319987773895,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 0.2712,
      "step": 390
    },
    {
      "epoch": 0.0951692567160583,
      "grad_norm": 0.5771711468696594,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 0.2676,
      "step": 395
    },
    {
      "epoch": 0.09637393085170462,
      "grad_norm": 0.6342702507972717,
      "learning_rate": 0.0,
      "loss": 0.2681,
      "step": 400
    },
    {
      "epoch": 0.09637393085170462,
      "eval_loss": 0.2801865339279175,
      "eval_runtime": 54.7085,
      "eval_samples_per_second": 127.768,
      "eval_steps_per_second": 15.976,
      "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
}