{
  "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": 6.4533820152282715,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.9693,
      "step": 5
    },
    {
      "epoch": 0.05685856432125089,
      "grad_norm": 4.657992839813232,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.7795,
      "step": 10
    },
    {
      "epoch": 0.08528784648187633,
      "grad_norm": 2.398066997528076,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.4535,
      "step": 15
    },
    {
      "epoch": 0.11371712864250177,
      "grad_norm": 1.7500923871994019,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.4519,
      "step": 20
    },
    {
      "epoch": 0.14214641080312723,
      "grad_norm": 1.989443063735962,
      "learning_rate": 7.142857142857143e-05,
      "loss": 0.4128,
      "step": 25
    },
    {
      "epoch": 0.17057569296375266,
      "grad_norm": 1.1362711191177368,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.3446,
      "step": 30
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 1.1770528554916382,
      "learning_rate": 0.0001,
      "loss": 0.3253,
      "step": 35
    },
    {
      "epoch": 0.19900497512437812,
      "eval_loss": 0.28751906752586365,
      "eval_runtime": 239.7962,
      "eval_samples_per_second": 10.426,
      "eval_steps_per_second": 10.426,
      "step": 35
    },
    {
      "epoch": 0.22743425728500355,
      "grad_norm": 1.1288448572158813,
      "learning_rate": 9.993784606094612e-05,
      "loss": 0.3065,
      "step": 40
    },
    {
      "epoch": 0.255863539445629,
      "grad_norm": 1.0276695489883423,
      "learning_rate": 9.975153876827008e-05,
      "loss": 0.302,
      "step": 45
    },
    {
      "epoch": 0.28429282160625446,
      "grad_norm": 1.2982385158538818,
      "learning_rate": 9.944154131125642e-05,
      "loss": 0.307,
      "step": 50
    },
    {
      "epoch": 0.31272210376687987,
      "grad_norm": 1.4258345365524292,
      "learning_rate": 9.900862439242719e-05,
      "loss": 0.2908,
      "step": 55
    },
    {
      "epoch": 0.3411513859275053,
      "grad_norm": 0.7898867726325989,
      "learning_rate": 9.84538643114539e-05,
      "loss": 0.3112,
      "step": 60
    },
    {
      "epoch": 0.3695806680881308,
      "grad_norm": 0.9717791676521301,
      "learning_rate": 9.777864028930705e-05,
      "loss": 0.2596,
      "step": 65
    },
    {
      "epoch": 0.39800995024875624,
      "grad_norm": 1.0619926452636719,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2868,
      "step": 70
    },
    {
      "epoch": 0.39800995024875624,
      "eval_loss": 0.2600123882293701,
      "eval_runtime": 240.5378,
      "eval_samples_per_second": 10.393,
      "eval_steps_per_second": 10.393,
      "step": 70
    },
    {
      "epoch": 0.42643923240938164,
      "grad_norm": 0.8634427189826965,
      "learning_rate": 9.607381059352038e-05,
      "loss": 0.2763,
      "step": 75
    },
    {
      "epoch": 0.4548685145700071,
      "grad_norm": 1.2894893884658813,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.254,
      "step": 80
    },
    {
      "epoch": 0.48329779673063256,
      "grad_norm": 1.4364824295043945,
      "learning_rate": 9.391107866851143e-05,
      "loss": 0.2834,
      "step": 85
    },
    {
      "epoch": 0.511727078891258,
      "grad_norm": 0.9127787947654724,
      "learning_rate": 9.266454408160779e-05,
      "loss": 0.2509,
      "step": 90
    },
    {
      "epoch": 0.5401563610518835,
      "grad_norm": 0.9939984083175659,
      "learning_rate": 9.131193871579975e-05,
      "loss": 0.266,
      "step": 95
    },
    {
      "epoch": 0.5685856432125089,
      "grad_norm": 1.184008002281189,
      "learning_rate": 8.985662536114613e-05,
      "loss": 0.2562,
      "step": 100
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 0.6923903226852417,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.2583,
      "step": 105
    },
    {
      "epoch": 0.5970149253731343,
      "eval_loss": 0.25079870223999023,
      "eval_runtime": 240.544,
      "eval_samples_per_second": 10.393,
      "eval_steps_per_second": 10.393,
      "step": 105
    },
    {
      "epoch": 0.6254442075337597,
      "grad_norm": 0.8162419199943542,
      "learning_rate": 8.665259359149132e-05,
      "loss": 0.2529,
      "step": 110
    },
    {
      "epoch": 0.6538734896943852,
      "grad_norm": 0.7928385734558105,
      "learning_rate": 8.491184090430364e-05,
      "loss": 0.2482,
      "step": 115
    },
    {
      "epoch": 0.6823027718550106,
      "grad_norm": 0.8485226035118103,
      "learning_rate": 8.308429187984297e-05,
      "loss": 0.244,
      "step": 120
    },
    {
      "epoch": 0.7107320540156361,
      "grad_norm": 0.8197255730628967,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.2453,
      "step": 125
    },
    {
      "epoch": 0.7391613361762616,
      "grad_norm": 0.9954875707626343,
      "learning_rate": 7.91871836117395e-05,
      "loss": 0.2451,
      "step": 130
    },
    {
      "epoch": 0.767590618336887,
      "grad_norm": 1.4009358882904053,
      "learning_rate": 7.712731319328798e-05,
      "loss": 0.2749,
      "step": 135
    },
    {
      "epoch": 0.7960199004975125,
      "grad_norm": 0.8014578819274902,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2559,
      "step": 140
    },
    {
      "epoch": 0.7960199004975125,
      "eval_loss": 0.2278721183538437,
      "eval_runtime": 239.2855,
      "eval_samples_per_second": 10.448,
      "eval_steps_per_second": 10.448,
      "step": 140
    },
    {
      "epoch": 0.8244491826581379,
      "grad_norm": 1.1141350269317627,
      "learning_rate": 7.281053286765815e-05,
      "loss": 0.2483,
      "step": 145
    },
    {
      "epoch": 0.8528784648187633,
      "grad_norm": 0.9138433933258057,
      "learning_rate": 7.056435515653059e-05,
      "loss": 0.2666,
      "step": 150
    },
    {
      "epoch": 0.8813077469793887,
      "grad_norm": 0.5915958285331726,
      "learning_rate": 6.826705121831976e-05,
      "loss": 0.2576,
      "step": 155
    },
    {
      "epoch": 0.9097370291400142,
      "grad_norm": 0.724046528339386,
      "learning_rate": 6.592433251258423e-05,
      "loss": 0.2552,
      "step": 160
    },
    {
      "epoch": 0.9381663113006397,
      "grad_norm": 1.355237364768982,
      "learning_rate": 6.354202340715026e-05,
      "loss": 0.2287,
      "step": 165
    },
    {
      "epoch": 0.9665955934612651,
      "grad_norm": 1.1470948457717896,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.2469,
      "step": 170
    },
    {
      "epoch": 0.9950248756218906,
      "grad_norm": 0.7694109678268433,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.2516,
      "step": 175
    },
    {
      "epoch": 0.9950248756218906,
      "eval_loss": 0.22209325432777405,
      "eval_runtime": 239.4751,
      "eval_samples_per_second": 10.439,
      "eval_steps_per_second": 10.439,
      "step": 175
    },
    {
      "epoch": 1.023454157782516,
      "grad_norm": 0.8034222722053528,
      "learning_rate": 5.621718523237427e-05,
      "loss": 0.2339,
      "step": 180
    },
    {
      "epoch": 1.0518834399431414,
      "grad_norm": 0.7792671322822571,
      "learning_rate": 5.373650467932122e-05,
      "loss": 0.2192,
      "step": 185
    },
    {
      "epoch": 1.080312722103767,
      "grad_norm": 1.2179112434387207,
      "learning_rate": 5.124653458690365e-05,
      "loss": 0.2306,
      "step": 190
    },
    {
      "epoch": 1.1087420042643923,
      "grad_norm": 0.7679367065429688,
      "learning_rate": 4.875346541309637e-05,
      "loss": 0.213,
      "step": 195
    },
    {
      "epoch": 1.1371712864250179,
      "grad_norm": 0.7573937773704529,
      "learning_rate": 4.626349532067879e-05,
      "loss": 0.2306,
      "step": 200
    },
    {
      "epoch": 1.1656005685856432,
      "grad_norm": 0.8733441233634949,
      "learning_rate": 4.378281476762576e-05,
      "loss": 0.2235,
      "step": 205
    },
    {
      "epoch": 1.1940298507462686,
      "grad_norm": 0.7307979464530945,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.2086,
      "step": 210
    },
    {
      "epoch": 1.1940298507462686,
      "eval_loss": 0.22708775103092194,
      "eval_runtime": 239.5157,
      "eval_samples_per_second": 10.438,
      "eval_steps_per_second": 10.438,
      "step": 210
    },
    {
      "epoch": 1.2224591329068941,
      "grad_norm": 0.7165330052375793,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.2027,
      "step": 215
    },
    {
      "epoch": 1.2508884150675195,
      "grad_norm": 0.9405038952827454,
      "learning_rate": 3.6457976592849754e-05,
      "loss": 0.1961,
      "step": 220
    },
    {
      "epoch": 1.279317697228145,
      "grad_norm": 1.5330524444580078,
      "learning_rate": 3.4075667487415785e-05,
      "loss": 0.2274,
      "step": 225
    },
    {
      "epoch": 1.3077469793887704,
      "grad_norm": 0.8158367872238159,
      "learning_rate": 3.173294878168025e-05,
      "loss": 0.215,
      "step": 230
    },
    {
      "epoch": 1.336176261549396,
      "grad_norm": 0.6741064786911011,
      "learning_rate": 2.9435644843469436e-05,
      "loss": 0.2164,
      "step": 235
    },
    {
      "epoch": 1.3646055437100213,
      "grad_norm": 0.841311514377594,
      "learning_rate": 2.718946713234185e-05,
      "loss": 0.2213,
      "step": 240
    },
    {
      "epoch": 1.3930348258706466,
      "grad_norm": 0.8467437624931335,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.238,
      "step": 245
    },
    {
      "epoch": 1.3930348258706466,
      "eval_loss": 0.2183476835489273,
      "eval_runtime": 239.5588,
      "eval_samples_per_second": 10.436,
      "eval_steps_per_second": 10.436,
      "step": 245
    },
    {
      "epoch": 1.4214641080312722,
      "grad_norm": 0.8148757219314575,
      "learning_rate": 2.2872686806712035e-05,
      "loss": 0.2179,
      "step": 250
    },
    {
      "epoch": 1.4498933901918978,
      "grad_norm": 0.7469142079353333,
      "learning_rate": 2.0812816388260518e-05,
      "loss": 0.2057,
      "step": 255
    },
    {
      "epoch": 1.4783226723525231,
      "grad_norm": 0.8624520897865295,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.1965,
      "step": 260
    },
    {
      "epoch": 1.5067519545131485,
      "grad_norm": 0.6433588862419128,
      "learning_rate": 1.691570812015704e-05,
      "loss": 0.2171,
      "step": 265
    },
    {
      "epoch": 1.535181236673774,
      "grad_norm": 0.8499258756637573,
      "learning_rate": 1.5088159095696363e-05,
      "loss": 0.2217,
      "step": 270
    },
    {
      "epoch": 1.5636105188343994,
      "grad_norm": 1.1365426778793335,
      "learning_rate": 1.3347406408508695e-05,
      "loss": 0.2035,
      "step": 275
    },
    {
      "epoch": 1.5920398009950247,
      "grad_norm": 0.8611994981765747,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.2176,
      "step": 280
    },
    {
      "epoch": 1.5920398009950247,
      "eval_loss": 0.22061596810817719,
      "eval_runtime": 242.1258,
      "eval_samples_per_second": 10.325,
      "eval_steps_per_second": 10.325,
      "step": 280
    },
    {
      "epoch": 1.6204690831556503,
      "grad_norm": 1.0038255453109741,
      "learning_rate": 1.0143374638853891e-05,
      "loss": 0.2203,
      "step": 285
    },
    {
      "epoch": 1.6488983653162759,
      "grad_norm": 0.7821207642555237,
      "learning_rate": 8.688061284200266e-06,
      "loss": 0.2171,
      "step": 290
    },
    {
      "epoch": 1.6773276474769012,
      "grad_norm": 0.8067914247512817,
      "learning_rate": 7.33545591839222e-06,
      "loss": 0.2009,
      "step": 295
    },
    {
      "epoch": 1.7057569296375266,
      "grad_norm": 0.7486416697502136,
      "learning_rate": 6.088921331488568e-06,
      "loss": 0.2224,
      "step": 300
    },
    {
      "epoch": 1.7341862117981521,
      "grad_norm": 0.8486853241920471,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.224,
      "step": 305
    },
    {
      "epoch": 1.7626154939587777,
      "grad_norm": 0.7262605428695679,
      "learning_rate": 3.9261894064796135e-06,
      "loss": 0.1882,
      "step": 310
    },
    {
      "epoch": 1.7910447761194028,
      "grad_norm": 0.8881399631500244,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.2022,
      "step": 315
    },
    {
      "epoch": 1.7910447761194028,
      "eval_loss": 0.22089815139770508,
      "eval_runtime": 240.8241,
      "eval_samples_per_second": 10.381,
      "eval_steps_per_second": 10.381,
      "step": 315
    },
    {
      "epoch": 1.8194740582800284,
      "grad_norm": 0.7644193172454834,
      "learning_rate": 2.221359710692961e-06,
      "loss": 0.1922,
      "step": 320
    },
    {
      "epoch": 1.847903340440654,
      "grad_norm": 0.7930929660797119,
      "learning_rate": 1.5461356885461075e-06,
      "loss": 0.2081,
      "step": 325
    },
    {
      "epoch": 1.8763326226012793,
      "grad_norm": 1.0377033948898315,
      "learning_rate": 9.913756075728087e-07,
      "loss": 0.2067,
      "step": 330
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.7175566554069519,
      "learning_rate": 5.584586887435739e-07,
      "loss": 0.2221,
      "step": 335
    },
    {
      "epoch": 1.9331911869225302,
      "grad_norm": 0.8279063701629639,
      "learning_rate": 2.4846123172992954e-07,
      "loss": 0.2142,
      "step": 340
    },
    {
      "epoch": 1.9616204690831558,
      "grad_norm": 0.7256584167480469,
      "learning_rate": 6.215393905388278e-08,
      "loss": 0.2089,
      "step": 345
    },
    {
      "epoch": 1.9900497512437811,
      "grad_norm": 0.7735417485237122,
      "learning_rate": 0.0,
      "loss": 0.209,
      "step": 350
    },
    {
      "epoch": 1.9900497512437811,
      "eval_loss": 0.21909472346305847,
      "eval_runtime": 241.0763,
      "eval_samples_per_second": 10.37,
      "eval_steps_per_second": 10.37,
      "step": 350
    },
    {
      "epoch": 1.9900497512437811,
      "step": 350,
      "total_flos": 1.252589932587516e+18,
      "train_loss": 0.2665647494792938,
      "train_runtime": 19782.1685,
      "train_samples_per_second": 2.275,
      "train_steps_per_second": 0.018
    }
  ],
  "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": 1.252589932587516e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}