{
  "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": 49.6033,
      "eval_samples_per_second": 140.918,
      "eval_steps_per_second": 17.62,
      "step": 1
    },
    {
      "epoch": 0.0012046741356463078,
      "grad_norm": 1.0501099824905396,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 5.2061,
      "step": 5
    },
    {
      "epoch": 0.0024093482712926155,
      "grad_norm": 0.9017743468284607,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 5.2067,
      "step": 10
    },
    {
      "epoch": 0.003614022406938923,
      "grad_norm": 1.2880569696426392,
      "learning_rate": 5e-05,
      "loss": 5.246,
      "step": 15
    },
    {
      "epoch": 0.004818696542585231,
      "grad_norm": 1.3013567924499512,
      "learning_rate": 6.666666666666667e-05,
      "loss": 4.9928,
      "step": 20
    },
    {
      "epoch": 0.006023370678231539,
      "grad_norm": 1.3073419332504272,
      "learning_rate": 8.333333333333334e-05,
      "loss": 4.7026,
      "step": 25
    },
    {
      "epoch": 0.007228044813877846,
      "grad_norm": 1.76248037815094,
      "learning_rate": 0.0001,
      "loss": 4.2688,
      "step": 30
    },
    {
      "epoch": 0.008432718949524154,
      "grad_norm": 1.6442067623138428,
      "learning_rate": 9.995494831023409e-05,
      "loss": 3.4073,
      "step": 35
    },
    {
      "epoch": 0.009637393085170462,
      "grad_norm": 1.499051809310913,
      "learning_rate": 9.981987442712633e-05,
      "loss": 2.7618,
      "step": 40
    },
    {
      "epoch": 0.01084206722081677,
      "grad_norm": 1.3366233110427856,
      "learning_rate": 9.959502176294383e-05,
      "loss": 1.8808,
      "step": 45
    },
    {
      "epoch": 0.012046741356463078,
      "grad_norm": 1.3299202919006348,
      "learning_rate": 9.928079551738543e-05,
      "loss": 1.3071,
      "step": 50
    },
    {
      "epoch": 0.013251415492109385,
      "grad_norm": 1.0938165187835693,
      "learning_rate": 9.887776194738432e-05,
      "loss": 0.8839,
      "step": 55
    },
    {
      "epoch": 0.014456089627755691,
      "grad_norm": 1.5741374492645264,
      "learning_rate": 9.838664734667495e-05,
      "loss": 0.6882,
      "step": 60
    },
    {
      "epoch": 0.015660763763402,
      "grad_norm": 1.5812095403671265,
      "learning_rate": 9.780833673696254e-05,
      "loss": 0.5109,
      "step": 65
    },
    {
      "epoch": 0.01686543789904831,
      "grad_norm": 1.116866111755371,
      "learning_rate": 9.714387227305422e-05,
      "loss": 0.3742,
      "step": 70
    },
    {
      "epoch": 0.018070112034694615,
      "grad_norm": 1.1462064981460571,
      "learning_rate": 9.639445136482548e-05,
      "loss": 0.3226,
      "step": 75
    },
    {
      "epoch": 0.019274786170340924,
      "grad_norm": 1.208228588104248,
      "learning_rate": 9.55614245194068e-05,
      "loss": 0.3124,
      "step": 80
    },
    {
      "epoch": 0.02047946030598723,
      "grad_norm": 1.1284897327423096,
      "learning_rate": 9.464629290747842e-05,
      "loss": 0.291,
      "step": 85
    },
    {
      "epoch": 0.02168413444163354,
      "grad_norm": 0.9293462634086609,
      "learning_rate": 9.365070565805941e-05,
      "loss": 0.3135,
      "step": 90
    },
    {
      "epoch": 0.022888808577279846,
      "grad_norm": 1.147952675819397,
      "learning_rate": 9.257645688666556e-05,
      "loss": 0.2827,
      "step": 95
    },
    {
      "epoch": 0.024093482712926155,
      "grad_norm": 0.8131073117256165,
      "learning_rate": 9.142548246219212e-05,
      "loss": 0.2992,
      "step": 100
    },
    {
      "epoch": 0.024093482712926155,
      "eval_loss": 0.30220097303390503,
      "eval_runtime": 49.727,
      "eval_samples_per_second": 140.567,
      "eval_steps_per_second": 17.576,
      "step": 100
    },
    {
      "epoch": 0.02529815684857246,
      "grad_norm": 0.8790974020957947,
      "learning_rate": 9.019985651834703e-05,
      "loss": 0.3103,
      "step": 105
    },
    {
      "epoch": 0.02650283098421877,
      "grad_norm": 0.6411612629890442,
      "learning_rate": 8.890178771592199e-05,
      "loss": 0.2806,
      "step": 110
    },
    {
      "epoch": 0.027707505119865077,
      "grad_norm": 0.6550126671791077,
      "learning_rate": 8.753361526263621e-05,
      "loss": 0.2977,
      "step": 115
    },
    {
      "epoch": 0.028912179255511383,
      "grad_norm": 0.729946494102478,
      "learning_rate": 8.609780469772623e-05,
      "loss": 0.278,
      "step": 120
    },
    {
      "epoch": 0.030116853391157692,
      "grad_norm": 0.673554539680481,
      "learning_rate": 8.459694344887732e-05,
      "loss": 0.3069,
      "step": 125
    },
    {
      "epoch": 0.031321527526804,
      "grad_norm": 0.5400055646896362,
      "learning_rate": 8.303373616950408e-05,
      "loss": 0.2697,
      "step": 130
    },
    {
      "epoch": 0.03252620166245031,
      "grad_norm": 0.5848944783210754,
      "learning_rate": 8.141099986478212e-05,
      "loss": 0.2821,
      "step": 135
    },
    {
      "epoch": 0.03373087579809662,
      "grad_norm": 0.6077755093574524,
      "learning_rate": 7.973165881521434e-05,
      "loss": 0.3083,
      "step": 140
    },
    {
      "epoch": 0.03493554993374292,
      "grad_norm": 0.6799314618110657,
      "learning_rate": 7.799873930687978e-05,
      "loss": 0.2677,
      "step": 145
    },
    {
      "epoch": 0.03614022406938923,
      "grad_norm": 0.8506907224655151,
      "learning_rate": 7.621536417786159e-05,
      "loss": 0.2917,
      "step": 150
    },
    {
      "epoch": 0.03734489820503554,
      "grad_norm": 0.7229334712028503,
      "learning_rate": 7.438474719068173e-05,
      "loss": 0.2842,
      "step": 155
    },
    {
      "epoch": 0.03854957234068185,
      "grad_norm": 0.5894433259963989,
      "learning_rate": 7.251018724088367e-05,
      "loss": 0.2929,
      "step": 160
    },
    {
      "epoch": 0.03975424647632815,
      "grad_norm": 0.4831799864768982,
      "learning_rate": 7.059506241219965e-05,
      "loss": 0.2746,
      "step": 165
    },
    {
      "epoch": 0.04095892061197446,
      "grad_norm": 0.6661810278892517,
      "learning_rate": 6.864282388901544e-05,
      "loss": 0.2661,
      "step": 170
    },
    {
      "epoch": 0.04216359474762077,
      "grad_norm": 0.655542254447937,
      "learning_rate": 6.665698973710288e-05,
      "loss": 0.2984,
      "step": 175
    },
    {
      "epoch": 0.04336826888326708,
      "grad_norm": 0.6977773308753967,
      "learning_rate": 6.464113856382752e-05,
      "loss": 0.2716,
      "step": 180
    },
    {
      "epoch": 0.04457294301891338,
      "grad_norm": 0.7483444213867188,
      "learning_rate": 6.259890306925627e-05,
      "loss": 0.2806,
      "step": 185
    },
    {
      "epoch": 0.04577761715455969,
      "grad_norm": 0.6179220080375671,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 0.2644,
      "step": 190
    },
    {
      "epoch": 0.046982291290206,
      "grad_norm": 0.7248973846435547,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 0.2754,
      "step": 195
    },
    {
      "epoch": 0.04818696542585231,
      "grad_norm": 0.5180511474609375,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 0.2816,
      "step": 200
    },
    {
      "epoch": 0.04818696542585231,
      "eval_loss": 0.2891940772533417,
      "eval_runtime": 49.7145,
      "eval_samples_per_second": 140.603,
      "eval_steps_per_second": 17.58,
      "step": 200
    },
    {
      "epoch": 0.04939163956149861,
      "grad_norm": 0.717217743396759,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 0.2947,
      "step": 205
    },
    {
      "epoch": 0.05059631369714492,
      "grad_norm": 0.8364290595054626,
      "learning_rate": 5.212206015980742e-05,
      "loss": 0.2726,
      "step": 210
    },
    {
      "epoch": 0.05180098783279123,
      "grad_norm": 0.5089383721351624,
      "learning_rate": 5e-05,
      "loss": 0.2751,
      "step": 215
    },
    {
      "epoch": 0.05300566196843754,
      "grad_norm": 0.6700091361999512,
      "learning_rate": 4.78779398401926e-05,
      "loss": 0.2774,
      "step": 220
    },
    {
      "epoch": 0.054210336104083844,
      "grad_norm": 0.4948834180831909,
      "learning_rate": 4.575970377622456e-05,
      "loss": 0.281,
      "step": 225
    },
    {
      "epoch": 0.05541501023973015,
      "grad_norm": 0.3750030994415283,
      "learning_rate": 4.364910901265606e-05,
      "loss": 0.2616,
      "step": 230
    },
    {
      "epoch": 0.05661968437537646,
      "grad_norm": 0.5234203338623047,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 0.2533,
      "step": 235
    },
    {
      "epoch": 0.057824358511022765,
      "grad_norm": 0.6091147661209106,
      "learning_rate": 3.94660365002137e-05,
      "loss": 0.2839,
      "step": 240
    },
    {
      "epoch": 0.059029032646669075,
      "grad_norm": 0.47072502970695496,
      "learning_rate": 3.740109693074375e-05,
      "loss": 0.2761,
      "step": 245
    },
    {
      "epoch": 0.060233706782315384,
      "grad_norm": 0.39634305238723755,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 0.2782,
      "step": 250
    },
    {
      "epoch": 0.061438380917961694,
      "grad_norm": 0.4202629327774048,
      "learning_rate": 3.334301026289712e-05,
      "loss": 0.2804,
      "step": 255
    },
    {
      "epoch": 0.062643055053608,
      "grad_norm": 0.6114380955696106,
      "learning_rate": 3.135717611098458e-05,
      "loss": 0.2726,
      "step": 260
    },
    {
      "epoch": 0.06384772918925431,
      "grad_norm": 0.37326812744140625,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 0.268,
      "step": 265
    },
    {
      "epoch": 0.06505240332490062,
      "grad_norm": 0.48931899666786194,
      "learning_rate": 2.748981275911633e-05,
      "loss": 0.2643,
      "step": 270
    },
    {
      "epoch": 0.06625707746054692,
      "grad_norm": 0.5798832178115845,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 0.2539,
      "step": 275
    },
    {
      "epoch": 0.06746175159619323,
      "grad_norm": 0.540962815284729,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 0.2662,
      "step": 280
    },
    {
      "epoch": 0.06866642573183954,
      "grad_norm": 0.6189134120941162,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 0.2811,
      "step": 285
    },
    {
      "epoch": 0.06987109986748584,
      "grad_norm": 0.39256712794303894,
      "learning_rate": 2.026834118478567e-05,
      "loss": 0.2747,
      "step": 290
    },
    {
      "epoch": 0.07107577400313216,
      "grad_norm": 0.558190643787384,
      "learning_rate": 1.858900013521788e-05,
      "loss": 0.2635,
      "step": 295
    },
    {
      "epoch": 0.07228044813877846,
      "grad_norm": 0.8916624784469604,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 0.2721,
      "step": 300
    },
    {
      "epoch": 0.07228044813877846,
      "eval_loss": 0.2829170823097229,
      "eval_runtime": 49.6478,
      "eval_samples_per_second": 140.792,
      "eval_steps_per_second": 17.604,
      "step": 300
    },
    {
      "epoch": 0.07348512227442477,
      "grad_norm": 0.6186990737915039,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 0.2538,
      "step": 305
    },
    {
      "epoch": 0.07468979641007108,
      "grad_norm": 0.5772135257720947,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 0.261,
      "step": 310
    },
    {
      "epoch": 0.07589447054571738,
      "grad_norm": 0.7393772602081299,
      "learning_rate": 1.246638473736378e-05,
      "loss": 0.2702,
      "step": 315
    },
    {
      "epoch": 0.0770991446813637,
      "grad_norm": 0.49082431197166443,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 0.2562,
      "step": 320
    },
    {
      "epoch": 0.07830381881701,
      "grad_norm": 0.2409713864326477,
      "learning_rate": 9.800143481652979e-06,
      "loss": 0.2712,
      "step": 325
    },
    {
      "epoch": 0.0795084929526563,
      "grad_norm": 0.6244598031044006,
      "learning_rate": 8.574517537807897e-06,
      "loss": 0.266,
      "step": 330
    },
    {
      "epoch": 0.08071316708830262,
      "grad_norm": 0.44633162021636963,
      "learning_rate": 7.423543113334436e-06,
      "loss": 0.2725,
      "step": 335
    },
    {
      "epoch": 0.08191784122394892,
      "grad_norm": 0.4065309166908264,
      "learning_rate": 6.349294341940593e-06,
      "loss": 0.2799,
      "step": 340
    },
    {
      "epoch": 0.08312251535959522,
      "grad_norm": 0.3984888792037964,
      "learning_rate": 5.353707092521582e-06,
      "loss": 0.2763,
      "step": 345
    },
    {
      "epoch": 0.08432718949524154,
      "grad_norm": 0.3939869701862335,
      "learning_rate": 4.43857548059321e-06,
      "loss": 0.276,
      "step": 350
    },
    {
      "epoch": 0.08553186363088784,
      "grad_norm": 0.4459209442138672,
      "learning_rate": 3.605548635174533e-06,
      "loss": 0.2786,
      "step": 355
    },
    {
      "epoch": 0.08673653776653416,
      "grad_norm": 0.5801013708114624,
      "learning_rate": 2.85612772694579e-06,
      "loss": 0.2693,
      "step": 360
    },
    {
      "epoch": 0.08794121190218046,
      "grad_norm": 0.41877418756484985,
      "learning_rate": 2.191663263037458e-06,
      "loss": 0.2655,
      "step": 365
    },
    {
      "epoch": 0.08914588603782676,
      "grad_norm": 0.4572800397872925,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 0.2594,
      "step": 370
    },
    {
      "epoch": 0.09035056017347308,
      "grad_norm": 0.6014503240585327,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 0.2757,
      "step": 375
    },
    {
      "epoch": 0.09155523430911938,
      "grad_norm": 0.7533774375915527,
      "learning_rate": 7.192044826145771e-07,
      "loss": 0.268,
      "step": 380
    },
    {
      "epoch": 0.09275990844476568,
      "grad_norm": 0.6264715790748596,
      "learning_rate": 4.049782370561583e-07,
      "loss": 0.2657,
      "step": 385
    },
    {
      "epoch": 0.093964582580412,
      "grad_norm": 0.33361977338790894,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 0.2725,
      "step": 390
    },
    {
      "epoch": 0.0951692567160583,
      "grad_norm": 0.5748486518859863,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 0.2672,
      "step": 395
    },
    {
      "epoch": 0.09637393085170462,
      "grad_norm": 0.617462694644928,
      "learning_rate": 0.0,
      "loss": 0.2686,
      "step": 400
    },
    {
      "epoch": 0.09637393085170462,
      "eval_loss": 0.28005144000053406,
      "eval_runtime": 50.7695,
      "eval_samples_per_second": 137.681,
      "eval_steps_per_second": 17.215,
      "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
}