{
  "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": 14.865596771240234,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 1.887,
      "step": 5
    },
    {
      "epoch": 0.05685856432125089,
      "grad_norm": 8.584558486938477,
      "learning_rate": 2.857142857142857e-05,
      "loss": 1.5936,
      "step": 10
    },
    {
      "epoch": 0.08528784648187633,
      "grad_norm": 4.329889297485352,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.5385,
      "step": 15
    },
    {
      "epoch": 0.11371712864250177,
      "grad_norm": 1.5808465480804443,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.4072,
      "step": 20
    },
    {
      "epoch": 0.14214641080312723,
      "grad_norm": 1.9611109495162964,
      "learning_rate": 7.142857142857143e-05,
      "loss": 0.3629,
      "step": 25
    },
    {
      "epoch": 0.17057569296375266,
      "grad_norm": 0.6985721588134766,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.3385,
      "step": 30
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 0.5211701989173889,
      "learning_rate": 0.0001,
      "loss": 0.3051,
      "step": 35
    },
    {
      "epoch": 0.19900497512437812,
      "eval_loss": 0.25876832008361816,
      "eval_runtime": 1601.7861,
      "eval_samples_per_second": 1.561,
      "eval_steps_per_second": 1.561,
      "step": 35
    },
    {
      "epoch": 0.22743425728500355,
      "grad_norm": 0.7382380962371826,
      "learning_rate": 9.993784606094612e-05,
      "loss": 0.2997,
      "step": 40
    },
    {
      "epoch": 0.255863539445629,
      "grad_norm": 0.7649598121643066,
      "learning_rate": 9.975153876827008e-05,
      "loss": 0.2794,
      "step": 45
    },
    {
      "epoch": 0.28429282160625446,
      "grad_norm": 0.8737666606903076,
      "learning_rate": 9.944154131125642e-05,
      "loss": 0.2777,
      "step": 50
    },
    {
      "epoch": 0.31272210376687987,
      "grad_norm": 18.472232818603516,
      "learning_rate": 9.900862439242719e-05,
      "loss": 0.2866,
      "step": 55
    },
    {
      "epoch": 0.3411513859275053,
      "grad_norm": 0.9156910181045532,
      "learning_rate": 9.84538643114539e-05,
      "loss": 0.2993,
      "step": 60
    },
    {
      "epoch": 0.3695806680881308,
      "grad_norm": 0.5505309700965881,
      "learning_rate": 9.777864028930705e-05,
      "loss": 0.2459,
      "step": 65
    },
    {
      "epoch": 0.39800995024875624,
      "grad_norm": 0.6314955949783325,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2726,
      "step": 70
    },
    {
      "epoch": 0.39800995024875624,
      "eval_loss": 0.24190224707126617,
      "eval_runtime": 1601.1971,
      "eval_samples_per_second": 1.561,
      "eval_steps_per_second": 1.561,
      "step": 70
    },
    {
      "epoch": 0.42643923240938164,
      "grad_norm": 0.37724295258522034,
      "learning_rate": 9.607381059352038e-05,
      "loss": 0.2722,
      "step": 75
    },
    {
      "epoch": 0.4548685145700071,
      "grad_norm": 0.5261896848678589,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.2427,
      "step": 80
    },
    {
      "epoch": 0.48329779673063256,
      "grad_norm": 0.5982173681259155,
      "learning_rate": 9.391107866851143e-05,
      "loss": 0.2672,
      "step": 85
    },
    {
      "epoch": 0.511727078891258,
      "grad_norm": 0.5829192399978638,
      "learning_rate": 9.266454408160779e-05,
      "loss": 0.2195,
      "step": 90
    },
    {
      "epoch": 0.5401563610518835,
      "grad_norm": 0.5800922513008118,
      "learning_rate": 9.131193871579975e-05,
      "loss": 0.2454,
      "step": 95
    },
    {
      "epoch": 0.5685856432125089,
      "grad_norm": 0.6000517010688782,
      "learning_rate": 8.985662536114613e-05,
      "loss": 0.3725,
      "step": 100
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 0.5690158605575562,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.2387,
      "step": 105
    },
    {
      "epoch": 0.5970149253731343,
      "eval_loss": 0.23953676223754883,
      "eval_runtime": 1600.7721,
      "eval_samples_per_second": 1.562,
      "eval_steps_per_second": 1.562,
      "step": 105
    },
    {
      "epoch": 0.6254442075337597,
      "grad_norm": 0.38492974638938904,
      "learning_rate": 8.665259359149132e-05,
      "loss": 0.2324,
      "step": 110
    },
    {
      "epoch": 0.6538734896943852,
      "grad_norm": 0.9776778221130371,
      "learning_rate": 8.491184090430364e-05,
      "loss": 0.2409,
      "step": 115
    },
    {
      "epoch": 0.6823027718550106,
      "grad_norm": 0.6985746622085571,
      "learning_rate": 8.308429187984297e-05,
      "loss": 0.2512,
      "step": 120
    },
    {
      "epoch": 0.7107320540156361,
      "grad_norm": 0.38226836919784546,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.2347,
      "step": 125
    },
    {
      "epoch": 0.7391613361762616,
      "grad_norm": 0.5587658882141113,
      "learning_rate": 7.91871836117395e-05,
      "loss": 0.2357,
      "step": 130
    },
    {
      "epoch": 0.767590618336887,
      "grad_norm": 0.6417293548583984,
      "learning_rate": 7.712731319328798e-05,
      "loss": 0.2607,
      "step": 135
    },
    {
      "epoch": 0.7960199004975125,
      "grad_norm": 0.3534771502017975,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2508,
      "step": 140
    },
    {
      "epoch": 0.7960199004975125,
      "eval_loss": 0.22614409029483795,
      "eval_runtime": 1601.6762,
      "eval_samples_per_second": 1.561,
      "eval_steps_per_second": 1.561,
      "step": 140
    },
    {
      "epoch": 0.8244491826581379,
      "grad_norm": 0.4052274525165558,
      "learning_rate": 7.281053286765815e-05,
      "loss": 0.2338,
      "step": 145
    },
    {
      "epoch": 0.8528784648187633,
      "grad_norm": 0.544508695602417,
      "learning_rate": 7.056435515653059e-05,
      "loss": 0.2547,
      "step": 150
    },
    {
      "epoch": 0.8813077469793887,
      "grad_norm": 0.4221990406513214,
      "learning_rate": 6.826705121831976e-05,
      "loss": 0.2481,
      "step": 155
    },
    {
      "epoch": 0.9097370291400142,
      "grad_norm": 0.5856378078460693,
      "learning_rate": 6.592433251258423e-05,
      "loss": 0.2431,
      "step": 160
    },
    {
      "epoch": 0.9381663113006397,
      "grad_norm": 0.8348550796508789,
      "learning_rate": 6.354202340715026e-05,
      "loss": 0.228,
      "step": 165
    },
    {
      "epoch": 0.9665955934612651,
      "grad_norm": 0.45988309383392334,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.2229,
      "step": 170
    },
    {
      "epoch": 0.9950248756218906,
      "grad_norm": 0.3123863637447357,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.2356,
      "step": 175
    },
    {
      "epoch": 0.9950248756218906,
      "eval_loss": 0.21728534996509552,
      "eval_runtime": 1603.0018,
      "eval_samples_per_second": 1.56,
      "eval_steps_per_second": 1.56,
      "step": 175
    },
    {
      "epoch": 1.023454157782516,
      "grad_norm": 0.38809412717819214,
      "learning_rate": 5.621718523237427e-05,
      "loss": 0.2172,
      "step": 180
    },
    {
      "epoch": 1.0518834399431414,
      "grad_norm": 0.45351433753967285,
      "learning_rate": 5.373650467932122e-05,
      "loss": 0.2047,
      "step": 185
    },
    {
      "epoch": 1.080312722103767,
      "grad_norm": 0.6264550685882568,
      "learning_rate": 5.124653458690365e-05,
      "loss": 0.2212,
      "step": 190
    },
    {
      "epoch": 1.1087420042643923,
      "grad_norm": 0.40359142422676086,
      "learning_rate": 4.875346541309637e-05,
      "loss": 0.211,
      "step": 195
    },
    {
      "epoch": 1.1371712864250179,
      "grad_norm": 0.39740586280822754,
      "learning_rate": 4.626349532067879e-05,
      "loss": 0.2332,
      "step": 200
    },
    {
      "epoch": 1.1656005685856432,
      "grad_norm": 0.406650573015213,
      "learning_rate": 4.378281476762576e-05,
      "loss": 0.2216,
      "step": 205
    },
    {
      "epoch": 1.1940298507462686,
      "grad_norm": 0.32201454043388367,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.2079,
      "step": 210
    },
    {
      "epoch": 1.1940298507462686,
      "eval_loss": 0.22092726826667786,
      "eval_runtime": 1600.8467,
      "eval_samples_per_second": 1.562,
      "eval_steps_per_second": 1.562,
      "step": 210
    },
    {
      "epoch": 1.2224591329068941,
      "grad_norm": 0.5302402377128601,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.2088,
      "step": 215
    },
    {
      "epoch": 1.2508884150675195,
      "grad_norm": 0.45570725202560425,
      "learning_rate": 3.6457976592849754e-05,
      "loss": 0.1963,
      "step": 220
    },
    {
      "epoch": 1.279317697228145,
      "grad_norm": 0.5804539918899536,
      "learning_rate": 3.4075667487415785e-05,
      "loss": 0.2277,
      "step": 225
    },
    {
      "epoch": 1.3077469793887704,
      "grad_norm": 0.3645894229412079,
      "learning_rate": 3.173294878168025e-05,
      "loss": 0.2113,
      "step": 230
    },
    {
      "epoch": 1.336176261549396,
      "grad_norm": 0.34145060181617737,
      "learning_rate": 2.9435644843469436e-05,
      "loss": 0.2135,
      "step": 235
    },
    {
      "epoch": 1.3646055437100213,
      "grad_norm": 0.36927691102027893,
      "learning_rate": 2.718946713234185e-05,
      "loss": 0.2165,
      "step": 240
    },
    {
      "epoch": 1.3930348258706466,
      "grad_norm": 0.3815215826034546,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.2293,
      "step": 245
    },
    {
      "epoch": 1.3930348258706466,
      "eval_loss": 0.21432924270629883,
      "eval_runtime": 1602.526,
      "eval_samples_per_second": 1.56,
      "eval_steps_per_second": 1.56,
      "step": 245
    },
    {
      "epoch": 1.4214641080312722,
      "grad_norm": 0.7202007174491882,
      "learning_rate": 2.2872686806712035e-05,
      "loss": 0.2125,
      "step": 250
    },
    {
      "epoch": 1.4498933901918978,
      "grad_norm": 0.4522590935230255,
      "learning_rate": 2.0812816388260518e-05,
      "loss": 0.2045,
      "step": 255
    },
    {
      "epoch": 1.4783226723525231,
      "grad_norm": 0.4174804091453552,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.1835,
      "step": 260
    },
    {
      "epoch": 1.5067519545131485,
      "grad_norm": 0.34801849722862244,
      "learning_rate": 1.691570812015704e-05,
      "loss": 0.2045,
      "step": 265
    },
    {
      "epoch": 1.535181236673774,
      "grad_norm": 0.4167223870754242,
      "learning_rate": 1.5088159095696363e-05,
      "loss": 0.2137,
      "step": 270
    },
    {
      "epoch": 1.5636105188343994,
      "grad_norm": 0.5468845367431641,
      "learning_rate": 1.3347406408508695e-05,
      "loss": 0.1994,
      "step": 275
    },
    {
      "epoch": 1.5920398009950247,
      "grad_norm": 0.4134819209575653,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.2129,
      "step": 280
    },
    {
      "epoch": 1.5920398009950247,
      "eval_loss": 0.2167833000421524,
      "eval_runtime": 1604.4756,
      "eval_samples_per_second": 1.558,
      "eval_steps_per_second": 1.558,
      "step": 280
    },
    {
      "epoch": 1.6204690831556503,
      "grad_norm": 0.5508995056152344,
      "learning_rate": 1.0143374638853891e-05,
      "loss": 0.2216,
      "step": 285
    },
    {
      "epoch": 1.6488983653162759,
      "grad_norm": 0.38880932331085205,
      "learning_rate": 8.688061284200266e-06,
      "loss": 0.2125,
      "step": 290
    },
    {
      "epoch": 1.6773276474769012,
      "grad_norm": 0.43846097588539124,
      "learning_rate": 7.33545591839222e-06,
      "loss": 0.1947,
      "step": 295
    },
    {
      "epoch": 1.7057569296375266,
      "grad_norm": 0.4228408634662628,
      "learning_rate": 6.088921331488568e-06,
      "loss": 0.2093,
      "step": 300
    },
    {
      "epoch": 1.7341862117981521,
      "grad_norm": 0.41265809535980225,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.2002,
      "step": 305
    },
    {
      "epoch": 1.7626154939587777,
      "grad_norm": 0.4552655518054962,
      "learning_rate": 3.9261894064796135e-06,
      "loss": 0.1749,
      "step": 310
    },
    {
      "epoch": 1.7910447761194028,
      "grad_norm": 0.4332776665687561,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.1974,
      "step": 315
    },
    {
      "epoch": 1.7910447761194028,
      "eval_loss": 0.21316008269786835,
      "eval_runtime": 1604.0523,
      "eval_samples_per_second": 1.559,
      "eval_steps_per_second": 1.559,
      "step": 315
    },
    {
      "epoch": 1.8194740582800284,
      "grad_norm": 0.3416159451007843,
      "learning_rate": 2.221359710692961e-06,
      "loss": 0.2004,
      "step": 320
    },
    {
      "epoch": 1.847903340440654,
      "grad_norm": 0.4291630983352661,
      "learning_rate": 1.5461356885461075e-06,
      "loss": 0.207,
      "step": 325
    },
    {
      "epoch": 1.8763326226012793,
      "grad_norm": 0.4680299162864685,
      "learning_rate": 9.913756075728087e-07,
      "loss": 0.1933,
      "step": 330
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.37417295575141907,
      "learning_rate": 5.584586887435739e-07,
      "loss": 0.2096,
      "step": 335
    },
    {
      "epoch": 1.9331911869225302,
      "grad_norm": 0.3924560844898224,
      "learning_rate": 2.4846123172992954e-07,
      "loss": 0.1997,
      "step": 340
    },
    {
      "epoch": 1.9616204690831558,
      "grad_norm": 0.492671400308609,
      "learning_rate": 6.215393905388278e-08,
      "loss": 0.2084,
      "step": 345
    },
    {
      "epoch": 1.9900497512437811,
      "grad_norm": 0.40119969844818115,
      "learning_rate": 0.0,
      "loss": 0.2068,
      "step": 350
    },
    {
      "epoch": 1.9900497512437811,
      "eval_loss": 0.2134595662355423,
      "eval_runtime": 1604.7077,
      "eval_samples_per_second": 1.558,
      "eval_steps_per_second": 1.558,
      "step": 350
    },
    {
      "epoch": 1.9900497512437811,
      "step": 350,
      "total_flos": 1.1585132109994918e+19,
      "train_loss": 0.2844532297338758,
      "train_runtime": 63902.5638,
      "train_samples_per_second": 0.704,
      "train_steps_per_second": 0.005
    }
  ],
  "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": 1.1585132109994918e+19,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}