{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9900497512437811,
  "eval_steps": 35,
  "global_step": 350,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.028429282160625444,
      "grad_norm": 2.917722702026367,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 1.3615,
      "step": 5
    },
    {
      "epoch": 0.05685856432125089,
      "grad_norm": 2.65405011177063,
      "learning_rate": 2.857142857142857e-05,
      "loss": 1.2182,
      "step": 10
    },
    {
      "epoch": 0.08528784648187633,
      "grad_norm": 4.0127272605896,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.8944,
      "step": 15
    },
    {
      "epoch": 0.11371712864250177,
      "grad_norm": 0.8177616000175476,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.512,
      "step": 20
    },
    {
      "epoch": 0.14214641080312723,
      "grad_norm": 0.3800067901611328,
      "learning_rate": 7.142857142857143e-05,
      "loss": 0.3435,
      "step": 25
    },
    {
      "epoch": 0.17057569296375266,
      "grad_norm": 0.3455258309841156,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.3027,
      "step": 30
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 0.3401183485984802,
      "learning_rate": 0.0001,
      "loss": 0.3045,
      "step": 35
    },
    {
      "epoch": 0.19900497512437812,
      "eval_loss": 0.2556740641593933,
      "eval_runtime": 1374.6693,
      "eval_samples_per_second": 1.819,
      "eval_steps_per_second": 1.819,
      "step": 35
    },
    {
      "epoch": 0.22743425728500355,
      "grad_norm": 0.3088541328907013,
      "learning_rate": 9.993784606094612e-05,
      "loss": 0.2799,
      "step": 40
    },
    {
      "epoch": 0.255863539445629,
      "grad_norm": 0.2526684105396271,
      "learning_rate": 9.975153876827008e-05,
      "loss": 0.2779,
      "step": 45
    },
    {
      "epoch": 0.28429282160625446,
      "grad_norm": 0.3618779182434082,
      "learning_rate": 9.944154131125642e-05,
      "loss": 0.2781,
      "step": 50
    },
    {
      "epoch": 0.31272210376687987,
      "grad_norm": 0.32333430647850037,
      "learning_rate": 9.900862439242719e-05,
      "loss": 0.2595,
      "step": 55
    },
    {
      "epoch": 0.3411513859275053,
      "grad_norm": 0.328197717666626,
      "learning_rate": 9.84538643114539e-05,
      "loss": 0.275,
      "step": 60
    },
    {
      "epoch": 0.3695806680881308,
      "grad_norm": 0.28067663311958313,
      "learning_rate": 9.777864028930705e-05,
      "loss": 0.2333,
      "step": 65
    },
    {
      "epoch": 0.39800995024875624,
      "grad_norm": 0.3941590487957001,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2524,
      "step": 70
    },
    {
      "epoch": 0.39800995024875624,
      "eval_loss": 0.23971079289913177,
      "eval_runtime": 1374.4109,
      "eval_samples_per_second": 1.819,
      "eval_steps_per_second": 1.819,
      "step": 70
    },
    {
      "epoch": 0.42643923240938164,
      "grad_norm": 0.2214515656232834,
      "learning_rate": 9.607381059352038e-05,
      "loss": 0.2585,
      "step": 75
    },
    {
      "epoch": 0.4548685145700071,
      "grad_norm": 0.27422434091567993,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.2122,
      "step": 80
    },
    {
      "epoch": 0.48329779673063256,
      "grad_norm": 0.28153732419013977,
      "learning_rate": 9.391107866851143e-05,
      "loss": 0.2397,
      "step": 85
    },
    {
      "epoch": 0.511727078891258,
      "grad_norm": 0.2967371344566345,
      "learning_rate": 9.266454408160779e-05,
      "loss": 0.2192,
      "step": 90
    },
    {
      "epoch": 0.5401563610518835,
      "grad_norm": 0.29277151823043823,
      "learning_rate": 9.131193871579975e-05,
      "loss": 0.234,
      "step": 95
    },
    {
      "epoch": 0.5685856432125089,
      "grad_norm": 0.30613964796066284,
      "learning_rate": 8.985662536114613e-05,
      "loss": 0.2376,
      "step": 100
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 0.27135342359542847,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.245,
      "step": 105
    },
    {
      "epoch": 0.5970149253731343,
      "eval_loss": 0.23002392053604126,
      "eval_runtime": 1375.9551,
      "eval_samples_per_second": 1.817,
      "eval_steps_per_second": 1.817,
      "step": 105
    },
    {
      "epoch": 0.6254442075337597,
      "grad_norm": 0.23706920444965363,
      "learning_rate": 8.665259359149132e-05,
      "loss": 0.2193,
      "step": 110
    },
    {
      "epoch": 0.6538734896943852,
      "grad_norm": 0.3904951214790344,
      "learning_rate": 8.491184090430364e-05,
      "loss": 0.231,
      "step": 115
    },
    {
      "epoch": 0.6823027718550106,
      "grad_norm": 0.23460106551647186,
      "learning_rate": 8.308429187984297e-05,
      "loss": 0.229,
      "step": 120
    },
    {
      "epoch": 0.7107320540156361,
      "grad_norm": 0.29704052209854126,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.2277,
      "step": 125
    },
    {
      "epoch": 0.7391613361762616,
      "grad_norm": 0.3585428297519684,
      "learning_rate": 7.91871836117395e-05,
      "loss": 0.2356,
      "step": 130
    },
    {
      "epoch": 0.767590618336887,
      "grad_norm": 0.3541390895843506,
      "learning_rate": 7.712731319328798e-05,
      "loss": 0.2521,
      "step": 135
    },
    {
      "epoch": 0.7960199004975125,
      "grad_norm": 0.3026750087738037,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2363,
      "step": 140
    },
    {
      "epoch": 0.7960199004975125,
      "eval_loss": 0.2129843682050705,
      "eval_runtime": 1375.37,
      "eval_samples_per_second": 1.818,
      "eval_steps_per_second": 1.818,
      "step": 140
    },
    {
      "epoch": 0.8244491826581379,
      "grad_norm": 0.3274117410182953,
      "learning_rate": 7.281053286765815e-05,
      "loss": 0.2308,
      "step": 145
    },
    {
      "epoch": 0.8528784648187633,
      "grad_norm": 0.2670952379703522,
      "learning_rate": 7.056435515653059e-05,
      "loss": 0.2456,
      "step": 150
    },
    {
      "epoch": 0.8813077469793887,
      "grad_norm": 0.36056894063949585,
      "learning_rate": 6.826705121831976e-05,
      "loss": 0.249,
      "step": 155
    },
    {
      "epoch": 0.9097370291400142,
      "grad_norm": 0.3259892761707306,
      "learning_rate": 6.592433251258423e-05,
      "loss": 0.2312,
      "step": 160
    },
    {
      "epoch": 0.9381663113006397,
      "grad_norm": 0.39926743507385254,
      "learning_rate": 6.354202340715026e-05,
      "loss": 0.2157,
      "step": 165
    },
    {
      "epoch": 0.9665955934612651,
      "grad_norm": 0.23705609142780304,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.2128,
      "step": 170
    },
    {
      "epoch": 0.9950248756218906,
      "grad_norm": 0.27746665477752686,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.2383,
      "step": 175
    },
    {
      "epoch": 0.9950248756218906,
      "eval_loss": 0.2247208058834076,
      "eval_runtime": 1375.4951,
      "eval_samples_per_second": 1.818,
      "eval_steps_per_second": 1.818,
      "step": 175
    },
    {
      "epoch": 1.023454157782516,
      "grad_norm": 0.2372225672006607,
      "learning_rate": 5.621718523237427e-05,
      "loss": 0.2187,
      "step": 180
    },
    {
      "epoch": 1.0518834399431414,
      "grad_norm": 0.2701272964477539,
      "learning_rate": 5.373650467932122e-05,
      "loss": 0.2024,
      "step": 185
    },
    {
      "epoch": 1.080312722103767,
      "grad_norm": 0.32787126302719116,
      "learning_rate": 5.124653458690365e-05,
      "loss": 0.221,
      "step": 190
    },
    {
      "epoch": 1.1087420042643923,
      "grad_norm": 0.2735784351825714,
      "learning_rate": 4.875346541309637e-05,
      "loss": 0.199,
      "step": 195
    },
    {
      "epoch": 1.1371712864250179,
      "grad_norm": 0.35804641246795654,
      "learning_rate": 4.626349532067879e-05,
      "loss": 0.2299,
      "step": 200
    },
    {
      "epoch": 1.1656005685856432,
      "grad_norm": 0.24261139333248138,
      "learning_rate": 4.378281476762576e-05,
      "loss": 0.2131,
      "step": 205
    },
    {
      "epoch": 1.1940298507462686,
      "grad_norm": 0.23894722759723663,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.2067,
      "step": 210
    },
    {
      "epoch": 1.1940298507462686,
      "eval_loss": 0.20743593573570251,
      "eval_runtime": 1374.8457,
      "eval_samples_per_second": 1.818,
      "eval_steps_per_second": 1.818,
      "step": 210
    },
    {
      "epoch": 1.2224591329068941,
      "grad_norm": 0.26743921637535095,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.2012,
      "step": 215
    },
    {
      "epoch": 1.2508884150675195,
      "grad_norm": 0.26504266262054443,
      "learning_rate": 3.6457976592849754e-05,
      "loss": 0.1927,
      "step": 220
    },
    {
      "epoch": 1.279317697228145,
      "grad_norm": 0.45054301619529724,
      "learning_rate": 3.4075667487415785e-05,
      "loss": 0.2153,
      "step": 225
    },
    {
      "epoch": 1.3077469793887704,
      "grad_norm": 0.2784373462200165,
      "learning_rate": 3.173294878168025e-05,
      "loss": 0.211,
      "step": 230
    },
    {
      "epoch": 1.336176261549396,
      "grad_norm": 0.2335204929113388,
      "learning_rate": 2.9435644843469436e-05,
      "loss": 0.2156,
      "step": 235
    },
    {
      "epoch": 1.3646055437100213,
      "grad_norm": 0.25453269481658936,
      "learning_rate": 2.718946713234185e-05,
      "loss": 0.2048,
      "step": 240
    },
    {
      "epoch": 1.3930348258706466,
      "grad_norm": 0.2633484899997711,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.2277,
      "step": 245
    },
    {
      "epoch": 1.3930348258706466,
      "eval_loss": 0.20937685668468475,
      "eval_runtime": 1374.1515,
      "eval_samples_per_second": 1.819,
      "eval_steps_per_second": 1.819,
      "step": 245
    },
    {
      "epoch": 1.4214641080312722,
      "grad_norm": 0.27278706431388855,
      "learning_rate": 2.2872686806712035e-05,
      "loss": 0.2073,
      "step": 250
    },
    {
      "epoch": 1.4498933901918978,
      "grad_norm": 0.2642519772052765,
      "learning_rate": 2.0812816388260518e-05,
      "loss": 0.2007,
      "step": 255
    },
    {
      "epoch": 1.4783226723525231,
      "grad_norm": 0.25261521339416504,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.1877,
      "step": 260
    },
    {
      "epoch": 1.5067519545131485,
      "grad_norm": 0.2179146111011505,
      "learning_rate": 1.691570812015704e-05,
      "loss": 0.1904,
      "step": 265
    },
    {
      "epoch": 1.535181236673774,
      "grad_norm": 0.35709136724472046,
      "learning_rate": 1.5088159095696363e-05,
      "loss": 0.2162,
      "step": 270
    },
    {
      "epoch": 1.5636105188343994,
      "grad_norm": 0.4146248996257782,
      "learning_rate": 1.3347406408508695e-05,
      "loss": 0.1985,
      "step": 275
    },
    {
      "epoch": 1.5920398009950247,
      "grad_norm": 0.27512213587760925,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.2057,
      "step": 280
    },
    {
      "epoch": 1.5920398009950247,
      "eval_loss": 0.20821616053581238,
      "eval_runtime": 1373.7304,
      "eval_samples_per_second": 1.82,
      "eval_steps_per_second": 1.82,
      "step": 280
    },
    {
      "epoch": 1.6204690831556503,
      "grad_norm": 0.4084846079349518,
      "learning_rate": 1.0143374638853891e-05,
      "loss": 0.2139,
      "step": 285
    },
    {
      "epoch": 1.6488983653162759,
      "grad_norm": 0.3040494918823242,
      "learning_rate": 8.688061284200266e-06,
      "loss": 0.2083,
      "step": 290
    },
    {
      "epoch": 1.6773276474769012,
      "grad_norm": 0.28483131527900696,
      "learning_rate": 7.33545591839222e-06,
      "loss": 0.185,
      "step": 295
    },
    {
      "epoch": 1.7057569296375266,
      "grad_norm": 0.2855469286441803,
      "learning_rate": 6.088921331488568e-06,
      "loss": 0.2131,
      "step": 300
    },
    {
      "epoch": 1.7341862117981521,
      "grad_norm": 0.3371677100658417,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.2071,
      "step": 305
    },
    {
      "epoch": 1.7626154939587777,
      "grad_norm": 0.26064884662628174,
      "learning_rate": 3.9261894064796135e-06,
      "loss": 0.1715,
      "step": 310
    },
    {
      "epoch": 1.7910447761194028,
      "grad_norm": 0.31194818019866943,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.1981,
      "step": 315
    },
    {
      "epoch": 1.7910447761194028,
      "eval_loss": 0.20436535775661469,
      "eval_runtime": 1372.7158,
      "eval_samples_per_second": 1.821,
      "eval_steps_per_second": 1.821,
      "step": 315
    },
    {
      "epoch": 1.8194740582800284,
      "grad_norm": 0.23213765025138855,
      "learning_rate": 2.221359710692961e-06,
      "loss": 0.1939,
      "step": 320
    },
    {
      "epoch": 1.847903340440654,
      "grad_norm": 0.3259161412715912,
      "learning_rate": 1.5461356885461075e-06,
      "loss": 0.2021,
      "step": 325
    },
    {
      "epoch": 1.8763326226012793,
      "grad_norm": 0.3195630609989166,
      "learning_rate": 9.913756075728087e-07,
      "loss": 0.1947,
      "step": 330
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.26338306069374084,
      "learning_rate": 5.584586887435739e-07,
      "loss": 0.2069,
      "step": 335
    },
    {
      "epoch": 1.9331911869225302,
      "grad_norm": 0.29805904626846313,
      "learning_rate": 2.4846123172992954e-07,
      "loss": 0.2079,
      "step": 340
    },
    {
      "epoch": 1.9616204690831558,
      "grad_norm": 0.300195574760437,
      "learning_rate": 6.215393905388278e-08,
      "loss": 0.2028,
      "step": 345
    },
    {
      "epoch": 1.9900497512437811,
      "grad_norm": 0.2901870906352997,
      "learning_rate": 0.0,
      "loss": 0.2107,
      "step": 350
    },
    {
      "epoch": 1.9900497512437811,
      "eval_loss": 0.20492638647556305,
      "eval_runtime": 1373.2127,
      "eval_samples_per_second": 1.821,
      "eval_steps_per_second": 1.821,
      "step": 350
    },
    {
      "epoch": 1.9900497512437811,
      "step": 350,
      "total_flos": 9.377647750828524e+18,
      "train_loss": 0.14908545851707458,
      "train_runtime": 36655.577,
      "train_samples_per_second": 1.228,
      "train_steps_per_second": 0.01
    }
  ],
  "logging_steps": 5,
  "max_steps": 350,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 35,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.377647750828524e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}