{
  "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": 11.854507446289062,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.9685,
      "step": 5
    },
    {
      "epoch": 0.05685856432125089,
      "grad_norm": 2.9244329929351807,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.5325,
      "step": 10
    },
    {
      "epoch": 0.08528784648187633,
      "grad_norm": 2.8243346214294434,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.2362,
      "step": 15
    },
    {
      "epoch": 0.11371712864250177,
      "grad_norm": 1.644755244255066,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.2163,
      "step": 20
    },
    {
      "epoch": 0.14214641080312723,
      "grad_norm": 5.001497268676758,
      "learning_rate": 7.142857142857143e-05,
      "loss": 0.2204,
      "step": 25
    },
    {
      "epoch": 0.17057569296375266,
      "grad_norm": 1.6563094854354858,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.2098,
      "step": 30
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 1.911417841911316,
      "learning_rate": 0.0001,
      "loss": 0.1803,
      "step": 35
    },
    {
      "epoch": 0.19900497512437812,
      "eval_loss": 0.16817478835582733,
      "eval_runtime": 318.5306,
      "eval_samples_per_second": 7.849,
      "eval_steps_per_second": 7.849,
      "step": 35
    },
    {
      "epoch": 0.22743425728500355,
      "grad_norm": 1.6745359897613525,
      "learning_rate": 9.993784606094612e-05,
      "loss": 0.1843,
      "step": 40
    },
    {
      "epoch": 0.255863539445629,
      "grad_norm": 0.9290557503700256,
      "learning_rate": 9.975153876827008e-05,
      "loss": 0.1751,
      "step": 45
    },
    {
      "epoch": 0.28429282160625446,
      "grad_norm": 1.3401949405670166,
      "learning_rate": 9.944154131125642e-05,
      "loss": 0.1722,
      "step": 50
    },
    {
      "epoch": 0.31272210376687987,
      "grad_norm": 0.9433913826942444,
      "learning_rate": 9.900862439242719e-05,
      "loss": 0.165,
      "step": 55
    },
    {
      "epoch": 0.3411513859275053,
      "grad_norm": 1.2080743312835693,
      "learning_rate": 9.84538643114539e-05,
      "loss": 0.1734,
      "step": 60
    },
    {
      "epoch": 0.3695806680881308,
      "grad_norm": 0.9101002812385559,
      "learning_rate": 9.777864028930705e-05,
      "loss": 0.1476,
      "step": 65
    },
    {
      "epoch": 0.39800995024875624,
      "grad_norm": 0.9633578658103943,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.1583,
      "step": 70
    },
    {
      "epoch": 0.39800995024875624,
      "eval_loss": 0.15481097996234894,
      "eval_runtime": 318.1907,
      "eval_samples_per_second": 7.857,
      "eval_steps_per_second": 7.857,
      "step": 70
    },
    {
      "epoch": 0.42643923240938164,
      "grad_norm": 0.9153623580932617,
      "learning_rate": 9.607381059352038e-05,
      "loss": 0.1632,
      "step": 75
    },
    {
      "epoch": 0.4548685145700071,
      "grad_norm": 0.9270277619361877,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1503,
      "step": 80
    },
    {
      "epoch": 0.48329779673063256,
      "grad_norm": 0.863593578338623,
      "learning_rate": 9.391107866851143e-05,
      "loss": 0.1527,
      "step": 85
    },
    {
      "epoch": 0.511727078891258,
      "grad_norm": 0.9579532146453857,
      "learning_rate": 9.266454408160779e-05,
      "loss": 0.1523,
      "step": 90
    },
    {
      "epoch": 0.5401563610518835,
      "grad_norm": 1.0070995092391968,
      "learning_rate": 9.131193871579975e-05,
      "loss": 0.1512,
      "step": 95
    },
    {
      "epoch": 0.5685856432125089,
      "grad_norm": 1.0314483642578125,
      "learning_rate": 8.985662536114613e-05,
      "loss": 0.1485,
      "step": 100
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 0.5653307437896729,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.1439,
      "step": 105
    },
    {
      "epoch": 0.5970149253731343,
      "eval_loss": 0.14900080859661102,
      "eval_runtime": 317.9816,
      "eval_samples_per_second": 7.862,
      "eval_steps_per_second": 7.862,
      "step": 105
    },
    {
      "epoch": 0.6254442075337597,
      "grad_norm": 0.6183350682258606,
      "learning_rate": 8.665259359149132e-05,
      "loss": 0.1459,
      "step": 110
    },
    {
      "epoch": 0.6538734896943852,
      "grad_norm": 0.667679488658905,
      "learning_rate": 8.491184090430364e-05,
      "loss": 0.1367,
      "step": 115
    },
    {
      "epoch": 0.6823027718550106,
      "grad_norm": 0.8107192516326904,
      "learning_rate": 8.308429187984297e-05,
      "loss": 0.1468,
      "step": 120
    },
    {
      "epoch": 0.7107320540156361,
      "grad_norm": 0.7757948637008667,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.1349,
      "step": 125
    },
    {
      "epoch": 0.7391613361762616,
      "grad_norm": 0.8467870354652405,
      "learning_rate": 7.91871836117395e-05,
      "loss": 0.1411,
      "step": 130
    },
    {
      "epoch": 0.767590618336887,
      "grad_norm": 1.0613672733306885,
      "learning_rate": 7.712731319328798e-05,
      "loss": 0.1663,
      "step": 135
    },
    {
      "epoch": 0.7960199004975125,
      "grad_norm": 0.7184066772460938,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1488,
      "step": 140
    },
    {
      "epoch": 0.7960199004975125,
      "eval_loss": 0.13560061156749725,
      "eval_runtime": 316.1201,
      "eval_samples_per_second": 7.908,
      "eval_steps_per_second": 7.908,
      "step": 140
    },
    {
      "epoch": 0.8244491826581379,
      "grad_norm": 0.5415666699409485,
      "learning_rate": 7.281053286765815e-05,
      "loss": 0.1426,
      "step": 145
    },
    {
      "epoch": 0.8528784648187633,
      "grad_norm": 0.7227004170417786,
      "learning_rate": 7.056435515653059e-05,
      "loss": 0.1542,
      "step": 150
    },
    {
      "epoch": 0.8813077469793887,
      "grad_norm": 0.47049930691719055,
      "learning_rate": 6.826705121831976e-05,
      "loss": 0.1455,
      "step": 155
    },
    {
      "epoch": 0.9097370291400142,
      "grad_norm": 0.4833870828151703,
      "learning_rate": 6.592433251258423e-05,
      "loss": 0.1376,
      "step": 160
    },
    {
      "epoch": 0.9381663113006397,
      "grad_norm": 1.1025599241256714,
      "learning_rate": 6.354202340715026e-05,
      "loss": 0.1352,
      "step": 165
    },
    {
      "epoch": 0.9665955934612651,
      "grad_norm": 0.6722602248191833,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.1402,
      "step": 170
    },
    {
      "epoch": 0.9950248756218906,
      "grad_norm": 0.6222644448280334,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.1385,
      "step": 175
    },
    {
      "epoch": 0.9950248756218906,
      "eval_loss": 0.136678546667099,
      "eval_runtime": 318.243,
      "eval_samples_per_second": 7.856,
      "eval_steps_per_second": 7.856,
      "step": 175
    },
    {
      "epoch": 1.023454157782516,
      "grad_norm": 0.49759426712989807,
      "learning_rate": 5.621718523237427e-05,
      "loss": 0.1232,
      "step": 180
    },
    {
      "epoch": 1.0518834399431414,
      "grad_norm": 0.6171165108680725,
      "learning_rate": 5.373650467932122e-05,
      "loss": 0.1148,
      "step": 185
    },
    {
      "epoch": 1.080312722103767,
      "grad_norm": 0.9642676711082458,
      "learning_rate": 5.124653458690365e-05,
      "loss": 0.1272,
      "step": 190
    },
    {
      "epoch": 1.1087420042643923,
      "grad_norm": 0.5711795091629028,
      "learning_rate": 4.875346541309637e-05,
      "loss": 0.111,
      "step": 195
    },
    {
      "epoch": 1.1371712864250179,
      "grad_norm": 0.5575156211853027,
      "learning_rate": 4.626349532067879e-05,
      "loss": 0.1284,
      "step": 200
    },
    {
      "epoch": 1.1656005685856432,
      "grad_norm": 0.5733321905136108,
      "learning_rate": 4.378281476762576e-05,
      "loss": 0.1214,
      "step": 205
    },
    {
      "epoch": 1.1940298507462686,
      "grad_norm": 0.47317320108413696,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.1092,
      "step": 210
    },
    {
      "epoch": 1.1940298507462686,
      "eval_loss": 0.13155004382133484,
      "eval_runtime": 318.2328,
      "eval_samples_per_second": 7.856,
      "eval_steps_per_second": 7.856,
      "step": 210
    },
    {
      "epoch": 1.2224591329068941,
      "grad_norm": 0.7402136921882629,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.1128,
      "step": 215
    },
    {
      "epoch": 1.2508884150675195,
      "grad_norm": 0.6445468068122864,
      "learning_rate": 3.6457976592849754e-05,
      "loss": 0.1064,
      "step": 220
    },
    {
      "epoch": 1.279317697228145,
      "grad_norm": 1.001204013824463,
      "learning_rate": 3.4075667487415785e-05,
      "loss": 0.1146,
      "step": 225
    },
    {
      "epoch": 1.3077469793887704,
      "grad_norm": 0.6902646422386169,
      "learning_rate": 3.173294878168025e-05,
      "loss": 0.1118,
      "step": 230
    },
    {
      "epoch": 1.336176261549396,
      "grad_norm": 0.5311295390129089,
      "learning_rate": 2.9435644843469436e-05,
      "loss": 0.1183,
      "step": 235
    },
    {
      "epoch": 1.3646055437100213,
      "grad_norm": 0.7023885250091553,
      "learning_rate": 2.718946713234185e-05,
      "loss": 0.1248,
      "step": 240
    },
    {
      "epoch": 1.3930348258706466,
      "grad_norm": 0.6486346125602722,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.1282,
      "step": 245
    },
    {
      "epoch": 1.3930348258706466,
      "eval_loss": 0.12762804329395294,
      "eval_runtime": 316.104,
      "eval_samples_per_second": 7.909,
      "eval_steps_per_second": 7.909,
      "step": 245
    },
    {
      "epoch": 1.4214641080312722,
      "grad_norm": 0.6740933060646057,
      "learning_rate": 2.2872686806712035e-05,
      "loss": 0.1147,
      "step": 250
    },
    {
      "epoch": 1.4498933901918978,
      "grad_norm": 0.6045389175415039,
      "learning_rate": 2.0812816388260518e-05,
      "loss": 0.1116,
      "step": 255
    },
    {
      "epoch": 1.4783226723525231,
      "grad_norm": 0.8824101686477661,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0991,
      "step": 260
    },
    {
      "epoch": 1.5067519545131485,
      "grad_norm": 0.6621524691581726,
      "learning_rate": 1.691570812015704e-05,
      "loss": 0.1137,
      "step": 265
    },
    {
      "epoch": 1.535181236673774,
      "grad_norm": 0.6356005668640137,
      "learning_rate": 1.5088159095696363e-05,
      "loss": 0.12,
      "step": 270
    },
    {
      "epoch": 1.5636105188343994,
      "grad_norm": 0.7734110951423645,
      "learning_rate": 1.3347406408508695e-05,
      "loss": 0.1055,
      "step": 275
    },
    {
      "epoch": 1.5920398009950247,
      "grad_norm": 0.7122759819030762,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.1135,
      "step": 280
    },
    {
      "epoch": 1.5920398009950247,
      "eval_loss": 0.1305658519268036,
      "eval_runtime": 318.0092,
      "eval_samples_per_second": 7.861,
      "eval_steps_per_second": 7.861,
      "step": 280
    },
    {
      "epoch": 1.6204690831556503,
      "grad_norm": 0.7382331490516663,
      "learning_rate": 1.0143374638853891e-05,
      "loss": 0.1153,
      "step": 285
    },
    {
      "epoch": 1.6488983653162759,
      "grad_norm": 0.5564413070678711,
      "learning_rate": 8.688061284200266e-06,
      "loss": 0.1137,
      "step": 290
    },
    {
      "epoch": 1.6773276474769012,
      "grad_norm": 0.6935514211654663,
      "learning_rate": 7.33545591839222e-06,
      "loss": 0.1002,
      "step": 295
    },
    {
      "epoch": 1.7057569296375266,
      "grad_norm": 0.5724297165870667,
      "learning_rate": 6.088921331488568e-06,
      "loss": 0.1159,
      "step": 300
    },
    {
      "epoch": 1.7341862117981521,
      "grad_norm": 0.6456014513969421,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.1151,
      "step": 305
    },
    {
      "epoch": 1.7626154939587777,
      "grad_norm": 0.6402171850204468,
      "learning_rate": 3.9261894064796135e-06,
      "loss": 0.0968,
      "step": 310
    },
    {
      "epoch": 1.7910447761194028,
      "grad_norm": 0.6542567014694214,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.1071,
      "step": 315
    },
    {
      "epoch": 1.7910447761194028,
      "eval_loss": 0.13068035244941711,
      "eval_runtime": 317.9913,
      "eval_samples_per_second": 7.862,
      "eval_steps_per_second": 7.862,
      "step": 315
    },
    {
      "epoch": 1.8194740582800284,
      "grad_norm": 0.5055389404296875,
      "learning_rate": 2.221359710692961e-06,
      "loss": 0.1052,
      "step": 320
    },
    {
      "epoch": 1.847903340440654,
      "grad_norm": 0.7156793475151062,
      "learning_rate": 1.5461356885461075e-06,
      "loss": 0.1098,
      "step": 325
    },
    {
      "epoch": 1.8763326226012793,
      "grad_norm": 0.7110255360603333,
      "learning_rate": 9.913756075728087e-07,
      "loss": 0.1062,
      "step": 330
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.6753076910972595,
      "learning_rate": 5.584586887435739e-07,
      "loss": 0.12,
      "step": 335
    },
    {
      "epoch": 1.9331911869225302,
      "grad_norm": 0.6932408213615417,
      "learning_rate": 2.4846123172992954e-07,
      "loss": 0.1109,
      "step": 340
    },
    {
      "epoch": 1.9616204690831558,
      "grad_norm": 0.7656528949737549,
      "learning_rate": 6.215393905388278e-08,
      "loss": 0.1168,
      "step": 345
    },
    {
      "epoch": 1.9900497512437811,
      "grad_norm": 0.5726015567779541,
      "learning_rate": 0.0,
      "loss": 0.1075,
      "step": 350
    },
    {
      "epoch": 1.9900497512437811,
      "eval_loss": 0.1294924020767212,
      "eval_runtime": 316.3526,
      "eval_samples_per_second": 7.903,
      "eval_steps_per_second": 7.903,
      "step": 350
    },
    {
      "epoch": 1.9900497512437811,
      "step": 350,
      "total_flos": 1.6683611739382088e+18,
      "train_loss": 0.1540991928747722,
      "train_runtime": 27601.9959,
      "train_samples_per_second": 1.63,
      "train_steps_per_second": 0.013
    }
  ],
  "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": 1.6683611739382088e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}