{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.7758046614872365,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03551609322974473,
      "grad_norm": 12.847548484802246,
      "learning_rate": 5e-05,
      "loss": 4.6931,
      "step": 1
    },
    {
      "epoch": 0.03551609322974473,
      "eval_loss": 5.996153354644775,
      "eval_runtime": 1.4302,
      "eval_samples_per_second": 34.96,
      "eval_steps_per_second": 9.09,
      "step": 1
    },
    {
      "epoch": 0.07103218645948946,
      "grad_norm": 14.917906761169434,
      "learning_rate": 0.0001,
      "loss": 5.4258,
      "step": 2
    },
    {
      "epoch": 0.10654827968923418,
      "grad_norm": 12.454079627990723,
      "learning_rate": 9.990365154573717e-05,
      "loss": 4.6077,
      "step": 3
    },
    {
      "epoch": 0.14206437291897892,
      "grad_norm": 7.093257427215576,
      "learning_rate": 9.961501876182148e-05,
      "loss": 3.1281,
      "step": 4
    },
    {
      "epoch": 0.17758046614872364,
      "grad_norm": 8.967534065246582,
      "learning_rate": 9.913533761814537e-05,
      "loss": 2.6663,
      "step": 5
    },
    {
      "epoch": 0.21309655937846836,
      "grad_norm": 7.362691879272461,
      "learning_rate": 9.846666218300807e-05,
      "loss": 2.6746,
      "step": 6
    },
    {
      "epoch": 0.2486126526082131,
      "grad_norm": 4.550023078918457,
      "learning_rate": 9.761185582727977e-05,
      "loss": 2.3725,
      "step": 7
    },
    {
      "epoch": 0.28412874583795783,
      "grad_norm": 10.55962085723877,
      "learning_rate": 9.657457896300791e-05,
      "loss": 2.3137,
      "step": 8
    },
    {
      "epoch": 0.3196448390677026,
      "grad_norm": 10.448192596435547,
      "learning_rate": 9.535927336897098e-05,
      "loss": 2.3299,
      "step": 9
    },
    {
      "epoch": 0.3551609322974473,
      "grad_norm": 3.725038766860962,
      "learning_rate": 9.397114317029975e-05,
      "loss": 2.0264,
      "step": 10
    },
    {
      "epoch": 0.390677025527192,
      "grad_norm": 6.806924343109131,
      "learning_rate": 9.241613255361455e-05,
      "loss": 2.2055,
      "step": 11
    },
    {
      "epoch": 0.4261931187569367,
      "grad_norm": 6.795745849609375,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.8821,
      "step": 12
    },
    {
      "epoch": 0.46170921198668147,
      "grad_norm": 3.854661226272583,
      "learning_rate": 8.883279133655399e-05,
      "loss": 1.8579,
      "step": 13
    },
    {
      "epoch": 0.4972253052164262,
      "grad_norm": 2.821107864379883,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.969,
      "step": 14
    },
    {
      "epoch": 0.532741398446171,
      "grad_norm": 2.6744842529296875,
      "learning_rate": 8.467056167950311e-05,
      "loss": 1.8684,
      "step": 15
    },
    {
      "epoch": 0.5682574916759157,
      "grad_norm": 2.6326615810394287,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.9566,
      "step": 16
    },
    {
      "epoch": 0.6037735849056604,
      "grad_norm": 2.0202972888946533,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.8665,
      "step": 17
    },
    {
      "epoch": 0.6392896781354052,
      "grad_norm": 2.3964056968688965,
      "learning_rate": 7.75e-05,
      "loss": 1.9297,
      "step": 18
    },
    {
      "epoch": 0.6748057713651499,
      "grad_norm": 2.168318271636963,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.7705,
      "step": 19
    },
    {
      "epoch": 0.7103218645948945,
      "grad_norm": 1.984513521194458,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.7141,
      "step": 20
    },
    {
      "epoch": 0.7458379578246392,
      "grad_norm": 2.0909554958343506,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.7412,
      "step": 21
    },
    {
      "epoch": 0.781354051054384,
      "grad_norm": 1.8733512163162231,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.7218,
      "step": 22
    },
    {
      "epoch": 0.8168701442841287,
      "grad_norm": 1.8428502082824707,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.8459,
      "step": 23
    },
    {
      "epoch": 0.8523862375138734,
      "grad_norm": 2.086453676223755,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.8321,
      "step": 24
    },
    {
      "epoch": 0.8879023307436182,
      "grad_norm": 2.0354926586151123,
      "learning_rate": 5.794314081535644e-05,
      "loss": 1.768,
      "step": 25
    },
    {
      "epoch": 0.8879023307436182,
      "eval_loss": 1.8483245372772217,
      "eval_runtime": 1.4767,
      "eval_samples_per_second": 33.859,
      "eval_steps_per_second": 8.803,
      "step": 25
    },
    {
      "epoch": 0.9234184239733629,
      "grad_norm": 2.222177743911743,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.6803,
      "step": 26
    },
    {
      "epoch": 0.9589345172031076,
      "grad_norm": 2.106823444366455,
      "learning_rate": 5.205685918464356e-05,
      "loss": 1.7212,
      "step": 27
    },
    {
      "epoch": 0.9944506104328524,
      "grad_norm": 2.1512210369110107,
      "learning_rate": 4.912632135009769e-05,
      "loss": 1.7802,
      "step": 28
    },
    {
      "epoch": 1.029966703662597,
      "grad_norm": 4.948949337005615,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 2.9527,
      "step": 29
    },
    {
      "epoch": 1.065482796892342,
      "grad_norm": 1.8342108726501465,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 1.637,
      "step": 30
    },
    {
      "epoch": 1.1009988901220866,
      "grad_norm": 1.786393165588379,
      "learning_rate": 4.053522406135775e-05,
      "loss": 1.6031,
      "step": 31
    },
    {
      "epoch": 1.1365149833518313,
      "grad_norm": 1.9454339742660522,
      "learning_rate": 3.777924554357096e-05,
      "loss": 1.3323,
      "step": 32
    },
    {
      "epoch": 1.172031076581576,
      "grad_norm": 2.2301857471466064,
      "learning_rate": 3.509700894014496e-05,
      "loss": 1.5233,
      "step": 33
    },
    {
      "epoch": 1.2075471698113207,
      "grad_norm": 2.044020891189575,
      "learning_rate": 3.250000000000001e-05,
      "loss": 1.5415,
      "step": 34
    },
    {
      "epoch": 1.2430632630410654,
      "grad_norm": 2.0642783641815186,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 1.4577,
      "step": 35
    },
    {
      "epoch": 1.2785793562708103,
      "grad_norm": 2.05415415763855,
      "learning_rate": 2.760573569460757e-05,
      "loss": 1.434,
      "step": 36
    },
    {
      "epoch": 1.314095449500555,
      "grad_norm": 2.0152251720428467,
      "learning_rate": 2.53294383204969e-05,
      "loss": 1.4434,
      "step": 37
    },
    {
      "epoch": 1.3496115427302997,
      "grad_norm": 2.1848814487457275,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 1.5678,
      "step": 38
    },
    {
      "epoch": 1.3851276359600444,
      "grad_norm": 2.1174445152282715,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 1.5425,
      "step": 39
    },
    {
      "epoch": 1.420643729189789,
      "grad_norm": 2.277348518371582,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 1.3887,
      "step": 40
    },
    {
      "epoch": 1.4561598224195338,
      "grad_norm": 2.1913950443267822,
      "learning_rate": 1.758386744638546e-05,
      "loss": 1.4529,
      "step": 41
    },
    {
      "epoch": 1.4916759156492785,
      "grad_norm": 2.30416202545166,
      "learning_rate": 1.602885682970026e-05,
      "loss": 1.4513,
      "step": 42
    },
    {
      "epoch": 1.5271920088790232,
      "grad_norm": 2.0522561073303223,
      "learning_rate": 1.464072663102903e-05,
      "loss": 1.3965,
      "step": 43
    },
    {
      "epoch": 1.5627081021087679,
      "grad_norm": 2.1286027431488037,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 1.5099,
      "step": 44
    },
    {
      "epoch": 1.5982241953385128,
      "grad_norm": 2.026170253753662,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 1.4889,
      "step": 45
    },
    {
      "epoch": 1.6337402885682575,
      "grad_norm": 2.003553628921509,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 1.415,
      "step": 46
    },
    {
      "epoch": 1.6692563817980022,
      "grad_norm": 2.1225321292877197,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 1.3807,
      "step": 47
    },
    {
      "epoch": 1.704772475027747,
      "grad_norm": 2.1674954891204834,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 1.3571,
      "step": 48
    },
    {
      "epoch": 1.7402885682574918,
      "grad_norm": 2.1650798320770264,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 1.5067,
      "step": 49
    },
    {
      "epoch": 1.7758046614872365,
      "grad_norm": 2.0062143802642822,
      "learning_rate": 1e-05,
      "loss": 1.3259,
      "step": 50
    },
    {
      "epoch": 1.7758046614872365,
      "eval_loss": 1.8066482543945312,
      "eval_runtime": 1.4758,
      "eval_samples_per_second": 33.88,
      "eval_steps_per_second": 8.809,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.589463780163584e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}