{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 344,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029133284777858703,
      "grad_norm": 73.69664001464844,
      "learning_rate": 1.142857142857143e-06,
      "loss": 0.8279,
      "step": 5
    },
    {
      "epoch": 0.05826656955571741,
      "grad_norm": 18.089183807373047,
      "learning_rate": 2.571428571428571e-06,
      "loss": 0.6482,
      "step": 10
    },
    {
      "epoch": 0.08739985433357611,
      "grad_norm": 13.27970027923584,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.486,
      "step": 15
    },
    {
      "epoch": 0.11653313911143481,
      "grad_norm": 15.923905372619629,
      "learning_rate": 5.428571428571429e-06,
      "loss": 0.3979,
      "step": 20
    },
    {
      "epoch": 0.14566642388929352,
      "grad_norm": 8.179045677185059,
      "learning_rate": 6.857142857142858e-06,
      "loss": 0.3618,
      "step": 25
    },
    {
      "epoch": 0.17479970866715222,
      "grad_norm": 14.475104331970215,
      "learning_rate": 8.285714285714287e-06,
      "loss": 0.4581,
      "step": 30
    },
    {
      "epoch": 0.20393299344501092,
      "grad_norm": 7.016964435577393,
      "learning_rate": 9.714285714285715e-06,
      "loss": 0.3754,
      "step": 35
    },
    {
      "epoch": 0.23306627822286963,
      "grad_norm": 11.657523155212402,
      "learning_rate": 9.995865881497621e-06,
      "loss": 0.3399,
      "step": 40
    },
    {
      "epoch": 0.26219956300072833,
      "grad_norm": 7.404115200042725,
      "learning_rate": 9.979082741033047e-06,
      "loss": 0.3636,
      "step": 45
    },
    {
      "epoch": 0.29133284777858703,
      "grad_norm": 6.842041015625,
      "learning_rate": 9.949435524132245e-06,
      "loss": 0.2615,
      "step": 50
    },
    {
      "epoch": 0.32046613255644574,
      "grad_norm": 11.180706977844238,
      "learning_rate": 9.907000828049001e-06,
      "loss": 0.3713,
      "step": 55
    },
    {
      "epoch": 0.34959941733430444,
      "grad_norm": 7.965044021606445,
      "learning_rate": 9.851888288072053e-06,
      "loss": 0.3645,
      "step": 60
    },
    {
      "epoch": 0.37873270211216314,
      "grad_norm": 5.142039775848389,
      "learning_rate": 9.784240294268756e-06,
      "loss": 0.3549,
      "step": 65
    },
    {
      "epoch": 0.40786598689002185,
      "grad_norm": 9.566123008728027,
      "learning_rate": 9.704231623602721e-06,
      "loss": 0.3537,
      "step": 70
    },
    {
      "epoch": 0.43699927166788055,
      "grad_norm": 7.709802150726318,
      "learning_rate": 9.612068988375898e-06,
      "loss": 0.3409,
      "step": 75
    },
    {
      "epoch": 0.46613255644573925,
      "grad_norm": 7.769692420959473,
      "learning_rate": 9.507990502161769e-06,
      "loss": 0.3313,
      "step": 80
    },
    {
      "epoch": 0.49526584122359796,
      "grad_norm": 6.162425994873047,
      "learning_rate": 9.392265064609455e-06,
      "loss": 0.3451,
      "step": 85
    },
    {
      "epoch": 0.5243991260014567,
      "grad_norm": 5.42238187789917,
      "learning_rate": 9.26519166670821e-06,
      "loss": 0.2925,
      "step": 90
    },
    {
      "epoch": 0.5535324107793154,
      "grad_norm": 6.669449806213379,
      "learning_rate": 9.127098618307177e-06,
      "loss": 0.255,
      "step": 95
    },
    {
      "epoch": 0.5826656955571741,
      "grad_norm": 8.019908905029297,
      "learning_rate": 8.978342699886289e-06,
      "loss": 0.3099,
      "step": 100
    },
    {
      "epoch": 0.6117989803350328,
      "grad_norm": 3.589531660079956,
      "learning_rate": 8.819308240769726e-06,
      "loss": 0.2269,
      "step": 105
    },
    {
      "epoch": 0.6409322651128915,
      "grad_norm": 4.610569000244141,
      "learning_rate": 8.650406126163553e-06,
      "loss": 0.2653,
      "step": 110
    },
    {
      "epoch": 0.6700655498907502,
      "grad_norm": 6.664720058441162,
      "learning_rate": 8.472072735582942e-06,
      "loss": 0.269,
      "step": 115
    },
    {
      "epoch": 0.6991988346686089,
      "grad_norm": 16.797792434692383,
      "learning_rate": 8.284768815411693e-06,
      "loss": 0.4095,
      "step": 120
    },
    {
      "epoch": 0.7283321194464676,
      "grad_norm": 5.306704521179199,
      "learning_rate": 8.088978288506923e-06,
      "loss": 0.2782,
      "step": 125
    },
    {
      "epoch": 0.7574654042243263,
      "grad_norm": 5.628018856048584,
      "learning_rate": 7.885207003924498e-06,
      "loss": 0.3129,
      "step": 130
    },
    {
      "epoch": 0.786598689002185,
      "grad_norm": 5.6005449295043945,
      "learning_rate": 7.673981429995372e-06,
      "loss": 0.3099,
      "step": 135
    },
    {
      "epoch": 0.8157319737800437,
      "grad_norm": 4.009358882904053,
      "learning_rate": 7.455847294129519e-06,
      "loss": 0.3116,
      "step": 140
    },
    {
      "epoch": 0.8448652585579024,
      "grad_norm": 5.827634811401367,
      "learning_rate": 7.23136817286163e-06,
      "loss": 0.3163,
      "step": 145
    },
    {
      "epoch": 0.8739985433357611,
      "grad_norm": 4.57042121887207,
      "learning_rate": 7.00112403578139e-06,
      "loss": 0.2765,
      "step": 150
    },
    {
      "epoch": 0.9031318281136198,
      "grad_norm": 6.091691493988037,
      "learning_rate": 6.765709747110274e-06,
      "loss": 0.2822,
      "step": 155
    },
    {
      "epoch": 0.9322651128914785,
      "grad_norm": 8.162725448608398,
      "learning_rate": 6.525733528796207e-06,
      "loss": 0.2809,
      "step": 160
    },
    {
      "epoch": 0.9613983976693372,
      "grad_norm": 11.629427909851074,
      "learning_rate": 6.281815389096903e-06,
      "loss": 0.3121,
      "step": 165
    },
    {
      "epoch": 0.9905316824471959,
      "grad_norm": 6.634247303009033,
      "learning_rate": 6.034585520711792e-06,
      "loss": 0.2421,
      "step": 170
    },
    {
      "epoch": 1.0174799708667153,
      "grad_norm": 5.846076488494873,
      "learning_rate": 5.7846826726012076e-06,
      "loss": 0.2224,
      "step": 175
    },
    {
      "epoch": 1.046613255644574,
      "grad_norm": 3.2555429935455322,
      "learning_rate": 5.532752499699381e-06,
      "loss": 0.1583,
      "step": 180
    },
    {
      "epoch": 1.0757465404224327,
      "grad_norm": 6.249210834503174,
      "learning_rate": 5.279445894785042e-06,
      "loss": 0.1885,
      "step": 185
    },
    {
      "epoch": 1.1048798252002914,
      "grad_norm": 4.369631290435791,
      "learning_rate": 5.025417306819348e-06,
      "loss": 0.1929,
      "step": 190
    },
    {
      "epoch": 1.13401310997815,
      "grad_norm": 7.5276899337768555,
      "learning_rate": 4.771323050096028e-06,
      "loss": 0.2046,
      "step": 195
    },
    {
      "epoch": 1.1631463947560088,
      "grad_norm": 4.717685699462891,
      "learning_rate": 4.5178196085721675e-06,
      "loss": 0.2059,
      "step": 200
    },
    {
      "epoch": 1.1922796795338675,
      "grad_norm": 7.297747611999512,
      "learning_rate": 4.265561939760671e-06,
      "loss": 0.2045,
      "step": 205
    },
    {
      "epoch": 1.2214129643117262,
      "grad_norm": 8.043347358703613,
      "learning_rate": 4.015201782566471e-06,
      "loss": 0.2349,
      "step": 210
    },
    {
      "epoch": 1.250546249089585,
      "grad_norm": 4.949600696563721,
      "learning_rate": 3.7673859734384153e-06,
      "loss": 0.1986,
      "step": 215
    },
    {
      "epoch": 1.2796795338674436,
      "grad_norm": 8.595296859741211,
      "learning_rate": 3.5227547751872548e-06,
      "loss": 0.1424,
      "step": 220
    },
    {
      "epoch": 1.3088128186453023,
      "grad_norm": 4.086767673492432,
      "learning_rate": 3.2819402227874364e-06,
      "loss": 0.1908,
      "step": 225
    },
    {
      "epoch": 1.337946103423161,
      "grad_norm": 8.891705513000488,
      "learning_rate": 3.0455644904365234e-06,
      "loss": 0.2572,
      "step": 230
    },
    {
      "epoch": 1.3670793882010197,
      "grad_norm": 7.054013252258301,
      "learning_rate": 2.8142382840911747e-06,
      "loss": 0.2184,
      "step": 235
    },
    {
      "epoch": 1.3962126729788784,
      "grad_norm": 5.363378524780273,
      "learning_rate": 2.588559263632719e-06,
      "loss": 0.2433,
      "step": 240
    },
    {
      "epoch": 1.4253459577567371,
      "grad_norm": 5.505529880523682,
      "learning_rate": 2.3691104987388923e-06,
      "loss": 0.177,
      "step": 245
    },
    {
      "epoch": 1.4544792425345958,
      "grad_norm": 4.260989665985107,
      "learning_rate": 2.156458962451164e-06,
      "loss": 0.2075,
      "step": 250
    },
    {
      "epoch": 1.4836125273124545,
      "grad_norm": 4.446367263793945,
      "learning_rate": 1.9511540663297284e-06,
      "loss": 0.1725,
      "step": 255
    },
    {
      "epoch": 1.5127458120903132,
      "grad_norm": 3.823702812194824,
      "learning_rate": 1.7537262409807476e-06,
      "loss": 0.1353,
      "step": 260
    },
    {
      "epoch": 1.541879096868172,
      "grad_norm": 4.295354843139648,
      "learning_rate": 1.5646855656232296e-06,
      "loss": 0.182,
      "step": 265
    },
    {
      "epoch": 1.5710123816460306,
      "grad_norm": 7.048524856567383,
      "learning_rate": 1.3845204502362442e-06,
      "loss": 0.1732,
      "step": 270
    },
    {
      "epoch": 1.6001456664238893,
      "grad_norm": 7.241790771484375,
      "learning_rate": 1.2136963736913117e-06,
      "loss": 0.1919,
      "step": 275
    },
    {
      "epoch": 1.629278951201748,
      "grad_norm": 5.843298435211182,
      "learning_rate": 1.0526546811301203e-06,
      "loss": 0.1666,
      "step": 280
    },
    {
      "epoch": 1.6584122359796067,
      "grad_norm": 4.440147399902344,
      "learning_rate": 9.018114436947373e-07,
      "loss": 0.1412,
      "step": 285
    },
    {
      "epoch": 1.6875455207574654,
      "grad_norm": 5.858366966247559,
      "learning_rate": 7.615563835563339e-07,
      "loss": 0.1833,
      "step": 290
    },
    {
      "epoch": 1.7166788055353241,
      "grad_norm": 7.964084148406982,
      "learning_rate": 6.322518670197142e-07,
      "loss": 0.1167,
      "step": 295
    },
    {
      "epoch": 1.7458120903131829,
      "grad_norm": 4.816522598266602,
      "learning_rate": 5.1423196830513e-07,
      "loss": 0.1117,
      "step": 300
    },
    {
      "epoch": 1.7749453750910416,
      "grad_norm": 4.06934928894043,
      "learning_rate": 4.078016064261847e-07,
      "loss": 0.2101,
      "step": 305
    },
    {
      "epoch": 1.8040786598689003,
      "grad_norm": 5.113325595855713,
      "learning_rate": 3.1323575739383716e-07,
      "loss": 0.1407,
      "step": 310
    },
    {
      "epoch": 1.833211944646759,
      "grad_norm": 5.883960247039795,
      "learning_rate": 2.307787437818365e-07,
      "loss": 0.1481,
      "step": 315
    },
    {
      "epoch": 1.8623452294246177,
      "grad_norm": 3.5390496253967285,
      "learning_rate": 1.6064360348912567e-07,
      "loss": 0.2063,
      "step": 320
    },
    {
      "epoch": 1.8914785142024764,
      "grad_norm": 6.701529026031494,
      "learning_rate": 1.0301153933006126e-07,
      "loss": 0.2186,
      "step": 325
    },
    {
      "epoch": 1.920611798980335,
      "grad_norm": 5.152849197387695,
      "learning_rate": 5.803145087451945e-08,
      "loss": 0.1676,
      "step": 330
    },
    {
      "epoch": 1.9497450837581938,
      "grad_norm": 6.510392665863037,
      "learning_rate": 2.581954974743117e-08,
      "loss": 0.1967,
      "step": 335
    },
    {
      "epoch": 1.9788783685360525,
      "grad_norm": 6.947445392608643,
      "learning_rate": 6.4590593816676875e-09,
      "loss": 0.1841,
      "step": 340
    },
    {
      "epoch": 2.0,
      "step": 344,
      "total_flos": 1.153078769590272e+16,
      "train_loss": 0.266781858580057,
      "train_runtime": 425.4095,
      "train_samples_per_second": 6.455,
      "train_steps_per_second": 0.809
    }
  ],
  "logging_steps": 5,
  "max_steps": 344,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.153078769590272e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}