{
  "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": 49.9747,
      "eval_samples_per_second": 139.871,
      "eval_steps_per_second": 17.489,
      "step": 1
    },
    {
      "epoch": 0.0012046741356463078,
      "grad_norm": 1.0792888402938843,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 5.2072,
      "step": 5
    },
    {
      "epoch": 0.0024093482712926155,
      "grad_norm": 0.9295633435249329,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 5.2054,
      "step": 10
    },
    {
      "epoch": 0.003614022406938923,
      "grad_norm": 1.2892745733261108,
      "learning_rate": 5e-05,
      "loss": 5.2404,
      "step": 15
    },
    {
      "epoch": 0.004818696542585231,
      "grad_norm": 1.3105595111846924,
      "learning_rate": 6.666666666666667e-05,
      "loss": 4.9878,
      "step": 20
    },
    {
      "epoch": 0.006023370678231539,
      "grad_norm": 1.310572862625122,
      "learning_rate": 8.333333333333334e-05,
      "loss": 4.6975,
      "step": 25
    },
    {
      "epoch": 0.007228044813877846,
      "grad_norm": 1.7426035404205322,
      "learning_rate": 0.0001,
      "loss": 4.26,
      "step": 30
    },
    {
      "epoch": 0.008432718949524154,
      "grad_norm": 1.6245442628860474,
      "learning_rate": 9.995494831023409e-05,
      "loss": 3.4022,
      "step": 35
    },
    {
      "epoch": 0.009637393085170462,
      "grad_norm": 1.5018351078033447,
      "learning_rate": 9.981987442712633e-05,
      "loss": 2.7623,
      "step": 40
    },
    {
      "epoch": 0.01084206722081677,
      "grad_norm": 1.3254516124725342,
      "learning_rate": 9.959502176294383e-05,
      "loss": 1.8828,
      "step": 45
    },
    {
      "epoch": 0.012046741356463078,
      "grad_norm": 1.3432636260986328,
      "learning_rate": 9.928079551738543e-05,
      "loss": 1.3058,
      "step": 50
    },
    {
      "epoch": 0.013251415492109385,
      "grad_norm": 1.2194437980651855,
      "learning_rate": 9.887776194738432e-05,
      "loss": 0.8751,
      "step": 55
    },
    {
      "epoch": 0.014456089627755691,
      "grad_norm": 1.6237940788269043,
      "learning_rate": 9.838664734667495e-05,
      "loss": 0.6913,
      "step": 60
    },
    {
      "epoch": 0.015660763763402,
      "grad_norm": 1.5743297338485718,
      "learning_rate": 9.780833673696254e-05,
      "loss": 0.5183,
      "step": 65
    },
    {
      "epoch": 0.01686543789904831,
      "grad_norm": 1.116608738899231,
      "learning_rate": 9.714387227305422e-05,
      "loss": 0.3818,
      "step": 70
    },
    {
      "epoch": 0.018070112034694615,
      "grad_norm": 1.1545337438583374,
      "learning_rate": 9.639445136482548e-05,
      "loss": 0.3259,
      "step": 75
    },
    {
      "epoch": 0.019274786170340924,
      "grad_norm": 1.1688393354415894,
      "learning_rate": 9.55614245194068e-05,
      "loss": 0.3142,
      "step": 80
    },
    {
      "epoch": 0.02047946030598723,
      "grad_norm": 1.1410008668899536,
      "learning_rate": 9.464629290747842e-05,
      "loss": 0.2933,
      "step": 85
    },
    {
      "epoch": 0.02168413444163354,
      "grad_norm": 0.946423351764679,
      "learning_rate": 9.365070565805941e-05,
      "loss": 0.3143,
      "step": 90
    },
    {
      "epoch": 0.022888808577279846,
      "grad_norm": 1.131354570388794,
      "learning_rate": 9.257645688666556e-05,
      "loss": 0.284,
      "step": 95
    },
    {
      "epoch": 0.024093482712926155,
      "grad_norm": 0.85454261302948,
      "learning_rate": 9.142548246219212e-05,
      "loss": 0.3004,
      "step": 100
    },
    {
      "epoch": 0.024093482712926155,
      "eval_loss": 0.3025200068950653,
      "eval_runtime": 50.0021,
      "eval_samples_per_second": 139.794,
      "eval_steps_per_second": 17.479,
      "step": 100
    },
    {
      "epoch": 0.02529815684857246,
      "grad_norm": 0.9261237382888794,
      "learning_rate": 9.019985651834703e-05,
      "loss": 0.3114,
      "step": 105
    },
    {
      "epoch": 0.02650283098421877,
      "grad_norm": 0.6699331998825073,
      "learning_rate": 8.890178771592199e-05,
      "loss": 0.2818,
      "step": 110
    },
    {
      "epoch": 0.027707505119865077,
      "grad_norm": 0.6681482791900635,
      "learning_rate": 8.753361526263621e-05,
      "loss": 0.2968,
      "step": 115
    },
    {
      "epoch": 0.028912179255511383,
      "grad_norm": 0.7507894039154053,
      "learning_rate": 8.609780469772623e-05,
      "loss": 0.2774,
      "step": 120
    },
    {
      "epoch": 0.030116853391157692,
      "grad_norm": 0.694439709186554,
      "learning_rate": 8.459694344887732e-05,
      "loss": 0.308,
      "step": 125
    },
    {
      "epoch": 0.031321527526804,
      "grad_norm": 0.5663962960243225,
      "learning_rate": 8.303373616950408e-05,
      "loss": 0.2707,
      "step": 130
    },
    {
      "epoch": 0.03252620166245031,
      "grad_norm": 0.5890136361122131,
      "learning_rate": 8.141099986478212e-05,
      "loss": 0.283,
      "step": 135
    },
    {
      "epoch": 0.03373087579809662,
      "grad_norm": 0.608544647693634,
      "learning_rate": 7.973165881521434e-05,
      "loss": 0.3108,
      "step": 140
    },
    {
      "epoch": 0.03493554993374292,
      "grad_norm": 0.6991100907325745,
      "learning_rate": 7.799873930687978e-05,
      "loss": 0.2684,
      "step": 145
    },
    {
      "epoch": 0.03614022406938923,
      "grad_norm": 0.8602761030197144,
      "learning_rate": 7.621536417786159e-05,
      "loss": 0.2925,
      "step": 150
    },
    {
      "epoch": 0.03734489820503554,
      "grad_norm": 0.7274888753890991,
      "learning_rate": 7.438474719068173e-05,
      "loss": 0.2829,
      "step": 155
    },
    {
      "epoch": 0.03854957234068185,
      "grad_norm": 0.576795220375061,
      "learning_rate": 7.251018724088367e-05,
      "loss": 0.2935,
      "step": 160
    },
    {
      "epoch": 0.03975424647632815,
      "grad_norm": 0.47064080834388733,
      "learning_rate": 7.059506241219965e-05,
      "loss": 0.2761,
      "step": 165
    },
    {
      "epoch": 0.04095892061197446,
      "grad_norm": 0.6882847547531128,
      "learning_rate": 6.864282388901544e-05,
      "loss": 0.2664,
      "step": 170
    },
    {
      "epoch": 0.04216359474762077,
      "grad_norm": 0.6872657537460327,
      "learning_rate": 6.665698973710288e-05,
      "loss": 0.2989,
      "step": 175
    },
    {
      "epoch": 0.04336826888326708,
      "grad_norm": 0.7068102955818176,
      "learning_rate": 6.464113856382752e-05,
      "loss": 0.2729,
      "step": 180
    },
    {
      "epoch": 0.04457294301891338,
      "grad_norm": 0.7935635447502136,
      "learning_rate": 6.259890306925627e-05,
      "loss": 0.2828,
      "step": 185
    },
    {
      "epoch": 0.04577761715455969,
      "grad_norm": 0.6559097170829773,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 0.2656,
      "step": 190
    },
    {
      "epoch": 0.046982291290206,
      "grad_norm": 0.7107484340667725,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 0.2753,
      "step": 195
    },
    {
      "epoch": 0.04818696542585231,
      "grad_norm": 0.5148826837539673,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 0.2823,
      "step": 200
    },
    {
      "epoch": 0.04818696542585231,
      "eval_loss": 0.2891713082790375,
      "eval_runtime": 50.0056,
      "eval_samples_per_second": 139.784,
      "eval_steps_per_second": 17.478,
      "step": 200
    },
    {
      "epoch": 0.04939163956149861,
      "grad_norm": 0.7411895990371704,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 0.2945,
      "step": 205
    },
    {
      "epoch": 0.05059631369714492,
      "grad_norm": 0.8631023168563843,
      "learning_rate": 5.212206015980742e-05,
      "loss": 0.2731,
      "step": 210
    },
    {
      "epoch": 0.05180098783279123,
      "grad_norm": 0.514038622379303,
      "learning_rate": 5e-05,
      "loss": 0.2749,
      "step": 215
    },
    {
      "epoch": 0.05300566196843754,
      "grad_norm": 0.6635034680366516,
      "learning_rate": 4.78779398401926e-05,
      "loss": 0.2762,
      "step": 220
    },
    {
      "epoch": 0.054210336104083844,
      "grad_norm": 0.48743897676467896,
      "learning_rate": 4.575970377622456e-05,
      "loss": 0.2811,
      "step": 225
    },
    {
      "epoch": 0.05541501023973015,
      "grad_norm": 0.37931758165359497,
      "learning_rate": 4.364910901265606e-05,
      "loss": 0.2609,
      "step": 230
    },
    {
      "epoch": 0.05661968437537646,
      "grad_norm": 0.522877037525177,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 0.2536,
      "step": 235
    },
    {
      "epoch": 0.057824358511022765,
      "grad_norm": 0.6197766661643982,
      "learning_rate": 3.94660365002137e-05,
      "loss": 0.2823,
      "step": 240
    },
    {
      "epoch": 0.059029032646669075,
      "grad_norm": 0.4717482030391693,
      "learning_rate": 3.740109693074375e-05,
      "loss": 0.276,
      "step": 245
    },
    {
      "epoch": 0.060233706782315384,
      "grad_norm": 0.41666683554649353,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 0.2776,
      "step": 250
    },
    {
      "epoch": 0.061438380917961694,
      "grad_norm": 0.4204334318637848,
      "learning_rate": 3.334301026289712e-05,
      "loss": 0.2808,
      "step": 255
    },
    {
      "epoch": 0.062643055053608,
      "grad_norm": 0.6174702644348145,
      "learning_rate": 3.135717611098458e-05,
      "loss": 0.2739,
      "step": 260
    },
    {
      "epoch": 0.06384772918925431,
      "grad_norm": 0.3634660840034485,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 0.2687,
      "step": 265
    },
    {
      "epoch": 0.06505240332490062,
      "grad_norm": 0.4894653260707855,
      "learning_rate": 2.748981275911633e-05,
      "loss": 0.264,
      "step": 270
    },
    {
      "epoch": 0.06625707746054692,
      "grad_norm": 0.5905735492706299,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 0.2545,
      "step": 275
    },
    {
      "epoch": 0.06746175159619323,
      "grad_norm": 0.558897078037262,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 0.2666,
      "step": 280
    },
    {
      "epoch": 0.06866642573183954,
      "grad_norm": 0.6371433138847351,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 0.2821,
      "step": 285
    },
    {
      "epoch": 0.06987109986748584,
      "grad_norm": 0.4050986170768738,
      "learning_rate": 2.026834118478567e-05,
      "loss": 0.2746,
      "step": 290
    },
    {
      "epoch": 0.07107577400313216,
      "grad_norm": 0.5596179366111755,
      "learning_rate": 1.858900013521788e-05,
      "loss": 0.2633,
      "step": 295
    },
    {
      "epoch": 0.07228044813877846,
      "grad_norm": 0.915583074092865,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 0.2718,
      "step": 300
    },
    {
      "epoch": 0.07228044813877846,
      "eval_loss": 0.2829594612121582,
      "eval_runtime": 52.054,
      "eval_samples_per_second": 134.284,
      "eval_steps_per_second": 16.79,
      "step": 300
    },
    {
      "epoch": 0.07348512227442477,
      "grad_norm": 0.6299046277999878,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 0.2525,
      "step": 305
    },
    {
      "epoch": 0.07468979641007108,
      "grad_norm": 0.5772097110748291,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 0.2614,
      "step": 310
    },
    {
      "epoch": 0.07589447054571738,
      "grad_norm": 0.7507283091545105,
      "learning_rate": 1.246638473736378e-05,
      "loss": 0.2716,
      "step": 315
    },
    {
      "epoch": 0.0770991446813637,
      "grad_norm": 0.5026983618736267,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 0.2567,
      "step": 320
    },
    {
      "epoch": 0.07830381881701,
      "grad_norm": 0.2531053423881531,
      "learning_rate": 9.800143481652979e-06,
      "loss": 0.2704,
      "step": 325
    },
    {
      "epoch": 0.0795084929526563,
      "grad_norm": 0.636057436466217,
      "learning_rate": 8.574517537807897e-06,
      "loss": 0.2643,
      "step": 330
    },
    {
      "epoch": 0.08071316708830262,
      "grad_norm": 0.47153595089912415,
      "learning_rate": 7.423543113334436e-06,
      "loss": 0.2736,
      "step": 335
    },
    {
      "epoch": 0.08191784122394892,
      "grad_norm": 0.3905453681945801,
      "learning_rate": 6.349294341940593e-06,
      "loss": 0.2789,
      "step": 340
    },
    {
      "epoch": 0.08312251535959522,
      "grad_norm": 0.40449318289756775,
      "learning_rate": 5.353707092521582e-06,
      "loss": 0.2764,
      "step": 345
    },
    {
      "epoch": 0.08432718949524154,
      "grad_norm": 0.4006820321083069,
      "learning_rate": 4.43857548059321e-06,
      "loss": 0.2745,
      "step": 350
    },
    {
      "epoch": 0.08553186363088784,
      "grad_norm": 0.4634566605091095,
      "learning_rate": 3.605548635174533e-06,
      "loss": 0.2792,
      "step": 355
    },
    {
      "epoch": 0.08673653776653416,
      "grad_norm": 0.5798748731613159,
      "learning_rate": 2.85612772694579e-06,
      "loss": 0.2695,
      "step": 360
    },
    {
      "epoch": 0.08794121190218046,
      "grad_norm": 0.42921146750450134,
      "learning_rate": 2.191663263037458e-06,
      "loss": 0.2658,
      "step": 365
    },
    {
      "epoch": 0.08914588603782676,
      "grad_norm": 0.46547698974609375,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 0.259,
      "step": 370
    },
    {
      "epoch": 0.09035056017347308,
      "grad_norm": 0.6249452829360962,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 0.2762,
      "step": 375
    },
    {
      "epoch": 0.09155523430911938,
      "grad_norm": 0.7665772438049316,
      "learning_rate": 7.192044826145771e-07,
      "loss": 0.2666,
      "step": 380
    },
    {
      "epoch": 0.09275990844476568,
      "grad_norm": 0.6290804743766785,
      "learning_rate": 4.049782370561583e-07,
      "loss": 0.2647,
      "step": 385
    },
    {
      "epoch": 0.093964582580412,
      "grad_norm": 0.3410860300064087,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 0.2724,
      "step": 390
    },
    {
      "epoch": 0.0951692567160583,
      "grad_norm": 0.5786365866661072,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 0.2678,
      "step": 395
    },
    {
      "epoch": 0.09637393085170462,
      "grad_norm": 0.6230505704879761,
      "learning_rate": 0.0,
      "loss": 0.2684,
      "step": 400
    },
    {
      "epoch": 0.09637393085170462,
      "eval_loss": 0.28017735481262207,
      "eval_runtime": 49.9297,
      "eval_samples_per_second": 139.997,
      "eval_steps_per_second": 17.505,
      "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
}