{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 44,
  "global_step": 44,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 3.7728848457336426,
      "learning_rate": 1e-05,
      "loss": 8.34375,
      "step": 1
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 3.084787130355835,
      "learning_rate": 9.987260573051268e-06,
      "loss": 7.0234375,
      "step": 2
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 2.8466055393218994,
      "learning_rate": 9.949107209404664e-06,
      "loss": 6.08984375,
      "step": 3
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 3.774195909500122,
      "learning_rate": 9.885734329855798e-06,
      "loss": 6.87890625,
      "step": 4
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 4.059106349945068,
      "learning_rate": 9.797464868072489e-06,
      "loss": 7.12109375,
      "step": 5
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 3.7631072998046875,
      "learning_rate": 9.68474862499881e-06,
      "loss": 6.3046875,
      "step": 6
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 3.927884817123413,
      "learning_rate": 9.548159976772593e-06,
      "loss": 5.96484375,
      "step": 7
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 4.121335983276367,
      "learning_rate": 9.388394947836278e-06,
      "loss": 5.453125,
      "step": 8
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 4.474863052368164,
      "learning_rate": 9.206267664155906e-06,
      "loss": 5.27734375,
      "step": 9
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 3.7031896114349365,
      "learning_rate": 9.002706204621802e-06,
      "loss": 4.576171875,
      "step": 10
    },
    {
      "epoch": 0.5,
      "grad_norm": 3.513298273086548,
      "learning_rate": 8.778747871771293e-06,
      "loss": 4.310546875,
      "step": 11
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 4.134742736816406,
      "learning_rate": 8.535533905932739e-06,
      "loss": 4.33984375,
      "step": 12
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 3.8901660442352295,
      "learning_rate": 8.274303669726427e-06,
      "loss": 3.921875,
      "step": 13
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 2.2645673751831055,
      "learning_rate": 7.996388332556735e-06,
      "loss": 3.314453125,
      "step": 14
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 2.048600912094116,
      "learning_rate": 7.703204087277989e-06,
      "loss": 3.20703125,
      "step": 15
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 2.4712393283843994,
      "learning_rate": 7.396244933600285e-06,
      "loss": 3.314453125,
      "step": 16
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 3.0463693141937256,
      "learning_rate": 7.0770750650094335e-06,
      "loss": 3.291015625,
      "step": 17
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 3.266054630279541,
      "learning_rate": 6.747320897995493e-06,
      "loss": 3.005859375,
      "step": 18
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 3.6807210445404053,
      "learning_rate": 6.408662784207149e-06,
      "loss": 2.7724609375,
      "step": 19
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 2.267378091812134,
      "learning_rate": 6.062826447764883e-06,
      "loss": 2.7060546875,
      "step": 20
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 1.1873700618743896,
      "learning_rate": 5.711574191366427e-06,
      "loss": 2.5791015625,
      "step": 21
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.1184544563293457,
      "learning_rate": 5.356695915996162e-06,
      "loss": 2.5419921875,
      "step": 22
    },
    {
      "epoch": 1.0454545454545454,
      "grad_norm": 1.0047101974487305,
      "learning_rate": 5e-06,
      "loss": 2.501953125,
      "step": 23
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.7801576852798462,
      "learning_rate": 4.643304084003839e-06,
      "loss": 2.4716796875,
      "step": 24
    },
    {
      "epoch": 1.1363636363636362,
      "grad_norm": 0.6709287166595459,
      "learning_rate": 4.2884258086335755e-06,
      "loss": 2.44140625,
      "step": 25
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 0.7361456155776978,
      "learning_rate": 3.937173552235117e-06,
      "loss": 2.439453125,
      "step": 26
    },
    {
      "epoch": 1.2272727272727273,
      "grad_norm": 0.7759865522384644,
      "learning_rate": 3.5913372157928515e-06,
      "loss": 2.4052734375,
      "step": 27
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.7013804316520691,
      "learning_rate": 3.252679102004509e-06,
      "loss": 2.3876953125,
      "step": 28
    },
    {
      "epoch": 1.3181818181818181,
      "grad_norm": 0.6193892955780029,
      "learning_rate": 2.9229249349905686e-06,
      "loss": 2.384765625,
      "step": 29
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.5779200196266174,
      "learning_rate": 2.603755066399718e-06,
      "loss": 2.3134765625,
      "step": 30
    },
    {
      "epoch": 1.4090909090909092,
      "grad_norm": 0.600002646446228,
      "learning_rate": 2.296795912722014e-06,
      "loss": 2.3310546875,
      "step": 31
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.5034871697425842,
      "learning_rate": 2.0036116674432653e-06,
      "loss": 2.3134765625,
      "step": 32
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.5135788917541504,
      "learning_rate": 1.7256963302735752e-06,
      "loss": 2.322265625,
      "step": 33
    },
    {
      "epoch": 1.5454545454545454,
      "grad_norm": 0.5401176810264587,
      "learning_rate": 1.4644660940672628e-06,
      "loss": 2.3193359375,
      "step": 34
    },
    {
      "epoch": 1.5909090909090908,
      "grad_norm": 0.5096068382263184,
      "learning_rate": 1.2212521282287093e-06,
      "loss": 2.3017578125,
      "step": 35
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.41300705075263977,
      "learning_rate": 9.972937953781985e-07,
      "loss": 2.263671875,
      "step": 36
    },
    {
      "epoch": 1.6818181818181817,
      "grad_norm": 0.41595977544784546,
      "learning_rate": 7.937323358440935e-07,
      "loss": 2.2021484375,
      "step": 37
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 0.47096025943756104,
      "learning_rate": 6.116050521637218e-07,
      "loss": 2.224609375,
      "step": 38
    },
    {
      "epoch": 1.7727272727272727,
      "grad_norm": 0.5018144249916077,
      "learning_rate": 4.5184002322740784e-07,
      "loss": 2.2705078125,
      "step": 39
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.43727609515190125,
      "learning_rate": 3.1525137500119207e-07,
      "loss": 2.3134765625,
      "step": 40
    },
    {
      "epoch": 1.8636363636363638,
      "grad_norm": 0.4339025318622589,
      "learning_rate": 2.0253513192751374e-07,
      "loss": 2.23828125,
      "step": 41
    },
    {
      "epoch": 1.9090909090909092,
      "grad_norm": 0.4514023959636688,
      "learning_rate": 1.1426567014420297e-07,
      "loss": 2.306640625,
      "step": 42
    },
    {
      "epoch": 1.9545454545454546,
      "grad_norm": 0.41209033131599426,
      "learning_rate": 5.089279059533658e-08,
      "loss": 2.294921875,
      "step": 43
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5065762996673584,
      "learning_rate": 1.2739426948732426e-08,
      "loss": 2.23583984375,
      "step": 44
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.29296875,
      "eval_runtime": 0.972,
      "eval_samples_per_second": 2.058,
      "eval_steps_per_second": 1.029,
      "step": 44
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 44,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.143867449075302e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}