{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9914040114613183,
  "eval_steps": 50,
  "global_step": 261,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05730659025787966,
      "grad_norm": 13.612731012431626,
      "learning_rate": 5e-07,
      "loss": 1.2694,
      "step": 5
    },
    {
      "epoch": 0.11461318051575932,
      "grad_norm": 8.505429082267508,
      "learning_rate": 1e-06,
      "loss": 1.1723,
      "step": 10
    },
    {
      "epoch": 0.17191977077363896,
      "grad_norm": 5.229519278318145,
      "learning_rate": 9.990212076323586e-07,
      "loss": 1.0671,
      "step": 15
    },
    {
      "epoch": 0.22922636103151864,
      "grad_norm": 3.9947603670699965,
      "learning_rate": 9.9608866266743e-07,
      "loss": 1.0138,
      "step": 20
    },
    {
      "epoch": 0.28653295128939826,
      "grad_norm": 3.900371267559279,
      "learning_rate": 9.912138465157323e-07,
      "loss": 1.0129,
      "step": 25
    },
    {
      "epoch": 0.3438395415472779,
      "grad_norm": 3.587740265290173,
      "learning_rate": 9.84415844908637e-07,
      "loss": 0.9834,
      "step": 30
    },
    {
      "epoch": 0.40114613180515757,
      "grad_norm": 3.5465531180374383,
      "learning_rate": 9.757212731744973e-07,
      "loss": 0.9669,
      "step": 35
    },
    {
      "epoch": 0.4584527220630373,
      "grad_norm": 3.5868905869199557,
      "learning_rate": 9.65164172035126e-07,
      "loss": 0.9694,
      "step": 40
    },
    {
      "epoch": 0.5157593123209169,
      "grad_norm": 3.42949608727936,
      "learning_rate": 9.527858743306018e-07,
      "loss": 0.9532,
      "step": 45
    },
    {
      "epoch": 0.5730659025787965,
      "grad_norm": 3.4836706161476148,
      "learning_rate": 9.386348431941952e-07,
      "loss": 0.9471,
      "step": 50
    },
    {
      "epoch": 0.5730659025787965,
      "eval_loss": 0.9284318089485168,
      "eval_runtime": 42.6858,
      "eval_samples_per_second": 58.076,
      "eval_steps_per_second": 0.914,
      "step": 50
    },
    {
      "epoch": 0.6303724928366762,
      "grad_norm": 3.5475576331396113,
      "learning_rate": 9.227664823109882e-07,
      "loss": 0.939,
      "step": 55
    },
    {
      "epoch": 0.6876790830945558,
      "grad_norm": 3.4823932284730343,
      "learning_rate": 9.052429190030588e-07,
      "loss": 0.9422,
      "step": 60
    },
    {
      "epoch": 0.7449856733524355,
      "grad_norm": 3.504161586419209,
      "learning_rate": 8.861327609904857e-07,
      "loss": 0.9429,
      "step": 65
    },
    {
      "epoch": 0.8022922636103151,
      "grad_norm": 3.5831153273903444,
      "learning_rate": 8.655108277804975e-07,
      "loss": 0.9253,
      "step": 70
    },
    {
      "epoch": 0.8595988538681948,
      "grad_norm": 3.4849359586215187,
      "learning_rate": 8.434578577364217e-07,
      "loss": 0.9285,
      "step": 75
    },
    {
      "epoch": 0.9169054441260746,
      "grad_norm": 3.945566817790106,
      "learning_rate": 8.200601919733105e-07,
      "loss": 0.8995,
      "step": 80
    },
    {
      "epoch": 0.9742120343839542,
      "grad_norm": 4.241462484260481,
      "learning_rate": 7.954094363178421e-07,
      "loss": 0.8951,
      "step": 85
    },
    {
      "epoch": 1.0315186246418337,
      "grad_norm": 4.381193820973214,
      "learning_rate": 7.696021026559849e-07,
      "loss": 0.8507,
      "step": 90
    },
    {
      "epoch": 1.0888252148997135,
      "grad_norm": 4.079439442006685,
      "learning_rate": 7.427392310726087e-07,
      "loss": 0.7966,
      "step": 95
    },
    {
      "epoch": 1.146131805157593,
      "grad_norm": 3.9309034286484152,
      "learning_rate": 7.149259942624286e-07,
      "loss": 0.7921,
      "step": 100
    },
    {
      "epoch": 1.146131805157593,
      "eval_loss": 0.8878535032272339,
      "eval_runtime": 42.2111,
      "eval_samples_per_second": 58.729,
      "eval_steps_per_second": 0.924,
      "step": 100
    },
    {
      "epoch": 1.2034383954154728,
      "grad_norm": 3.8824387052788545,
      "learning_rate": 6.862712857610811e-07,
      "loss": 0.7853,
      "step": 105
    },
    {
      "epoch": 1.2607449856733524,
      "grad_norm": 3.9703356398550897,
      "learning_rate": 6.568872936084788e-07,
      "loss": 0.7943,
      "step": 110
    },
    {
      "epoch": 1.3180515759312321,
      "grad_norm": 3.7052068664536657,
      "learning_rate": 6.26889061113621e-07,
      "loss": 0.7821,
      "step": 115
    },
    {
      "epoch": 1.3753581661891117,
      "grad_norm": 4.083661826698345,
      "learning_rate": 5.963940364405425e-07,
      "loss": 0.789,
      "step": 120
    },
    {
      "epoch": 1.4326647564469914,
      "grad_norm": 3.6717366050685425,
      "learning_rate": 5.655216127788472e-07,
      "loss": 0.7786,
      "step": 125
    },
    {
      "epoch": 1.4899713467048712,
      "grad_norm": 3.9393351724579673,
      "learning_rate": 5.343926608991379e-07,
      "loss": 0.7721,
      "step": 130
    },
    {
      "epoch": 1.5472779369627507,
      "grad_norm": 3.9510134927825815,
      "learning_rate": 5.031290559234649e-07,
      "loss": 0.7792,
      "step": 135
    },
    {
      "epoch": 1.6045845272206303,
      "grad_norm": 3.955872636060191,
      "learning_rate": 4.718532001635686e-07,
      "loss": 0.7751,
      "step": 140
    },
    {
      "epoch": 1.66189111747851,
      "grad_norm": 3.9126113945799896,
      "learning_rate": 4.406875438950861e-07,
      "loss": 0.7639,
      "step": 145
    },
    {
      "epoch": 1.7191977077363898,
      "grad_norm": 3.7773736719888986,
      "learning_rate": 4.097541059439698e-07,
      "loss": 0.7634,
      "step": 150
    },
    {
      "epoch": 1.7191977077363898,
      "eval_loss": 0.8642065525054932,
      "eval_runtime": 42.2075,
      "eval_samples_per_second": 58.734,
      "eval_steps_per_second": 0.924,
      "step": 150
    },
    {
      "epoch": 1.7765042979942693,
      "grad_norm": 3.8997816617752217,
      "learning_rate": 3.7917399596210535e-07,
      "loss": 0.769,
      "step": 155
    },
    {
      "epoch": 1.8338108882521489,
      "grad_norm": 3.790527862207605,
      "learning_rate": 3.490669402625007e-07,
      "loss": 0.7654,
      "step": 160
    },
    {
      "epoch": 1.8911174785100286,
      "grad_norm": 3.9519622867164457,
      "learning_rate": 3.195508130704795e-07,
      "loss": 0.7609,
      "step": 165
    },
    {
      "epoch": 1.9484240687679084,
      "grad_norm": 3.9887499398434625,
      "learning_rate": 2.9074117502611296e-07,
      "loss": 0.7561,
      "step": 170
    },
    {
      "epoch": 2.005730659025788,
      "grad_norm": 4.479124737500762,
      "learning_rate": 2.6275082074473075e-07,
      "loss": 0.7395,
      "step": 175
    },
    {
      "epoch": 2.0630372492836675,
      "grad_norm": 4.30255843532208,
      "learning_rate": 2.3568933720688543e-07,
      "loss": 0.6777,
      "step": 180
    },
    {
      "epoch": 2.1203438395415475,
      "grad_norm": 4.2850838721475775,
      "learning_rate": 2.096626747067527e-07,
      "loss": 0.668,
      "step": 185
    },
    {
      "epoch": 2.177650429799427,
      "grad_norm": 4.27894752208573,
      "learning_rate": 1.8477273203877398e-07,
      "loss": 0.6877,
      "step": 190
    },
    {
      "epoch": 2.2349570200573066,
      "grad_norm": 4.181872763790691,
      "learning_rate": 1.6111695754660664e-07,
      "loss": 0.684,
      "step": 195
    },
    {
      "epoch": 2.292263610315186,
      "grad_norm": 4.074063505059189,
      "learning_rate": 1.3878796759634542e-07,
      "loss": 0.6847,
      "step": 200
    },
    {
      "epoch": 2.292263610315186,
      "eval_loss": 0.861405611038208,
      "eval_runtime": 42.3254,
      "eval_samples_per_second": 58.57,
      "eval_steps_per_second": 0.921,
      "step": 200
    },
    {
      "epoch": 2.349570200573066,
      "grad_norm": 4.181385168106894,
      "learning_rate": 1.1787318396775186e-07,
      "loss": 0.6855,
      "step": 205
    },
    {
      "epoch": 2.4068767908309456,
      "grad_norm": 4.435888709429708,
      "learning_rate": 9.845449158317215e-08,
      "loss": 0.6917,
      "step": 210
    },
    {
      "epoch": 2.464183381088825,
      "grad_norm": 4.131014634407806,
      "learning_rate": 8.060791791418886e-08,
      "loss": 0.6697,
      "step": 215
    },
    {
      "epoch": 2.5214899713467047,
      "grad_norm": 4.172742524614935,
      "learning_rate": 6.440333532118503e-08,
      "loss": 0.684,
      "step": 220
    },
    {
      "epoch": 2.5787965616045847,
      "grad_norm": 4.2840818510970315,
      "learning_rate": 4.990418749121178e-08,
      "loss": 0.6741,
      "step": 225
    },
    {
      "epoch": 2.6361031518624642,
      "grad_norm": 4.308942481095818,
      "learning_rate": 3.716724104520247e-08,
      "loss": 0.6755,
      "step": 230
    },
    {
      "epoch": 2.693409742120344,
      "grad_norm": 4.0697930050384965,
      "learning_rate": 2.624236328703061e-08,
      "loss": 0.6954,
      "step": 235
    },
    {
      "epoch": 2.7507163323782233,
      "grad_norm": 3.977097437240088,
      "learning_rate": 1.7172326964564775e-08,
      "loss": 0.6717,
      "step": 240
    },
    {
      "epoch": 2.8080229226361033,
      "grad_norm": 4.224048431872294,
      "learning_rate": 9.992642807111484e-09,
      "loss": 0.6895,
      "step": 245
    },
    {
      "epoch": 2.865329512893983,
      "grad_norm": 4.227571057802346,
      "learning_rate": 4.7314204948923354e-09,
      "loss": 0.685,
      "step": 250
    },
    {
      "epoch": 2.865329512893983,
      "eval_loss": 0.8605780005455017,
      "eval_runtime": 42.2594,
      "eval_samples_per_second": 58.662,
      "eval_steps_per_second": 0.923,
      "step": 250
    },
    {
      "epoch": 2.9226361031518624,
      "grad_norm": 4.133004970094535,
      "learning_rate": 1.4092586048820575e-09,
      "loss": 0.678,
      "step": 255
    },
    {
      "epoch": 2.9799426934097424,
      "grad_norm": 4.1145286305129325,
      "learning_rate": 3.91639638886998e-11,
      "loss": 0.6876,
      "step": 260
    },
    {
      "epoch": 2.9914040114613183,
      "step": 261,
      "total_flos": 1538740350615552.0,
      "train_loss": 0.8157067728225299,
      "train_runtime": 3559.1971,
      "train_samples_per_second": 18.806,
      "train_steps_per_second": 0.073
    }
  ],
  "logging_steps": 5,
  "max_steps": 261,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1538740350615552.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}