{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 44,
  "global_step": 44,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022727272727272728,
      "grad_norm": 0.7660127878189087,
      "learning_rate": 1e-05,
      "loss": 1.6543,
      "step": 1
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 0.9602343440055847,
      "learning_rate": 9.987260573051268e-06,
      "loss": 1.8145,
      "step": 2
    },
    {
      "epoch": 0.06818181818181818,
      "grad_norm": 0.7751583456993103,
      "learning_rate": 9.949107209404664e-06,
      "loss": 1.6748,
      "step": 3
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 0.6850475668907166,
      "learning_rate": 9.885734329855798e-06,
      "loss": 1.6143,
      "step": 4
    },
    {
      "epoch": 0.11363636363636363,
      "grad_norm": 0.6464279890060425,
      "learning_rate": 9.797464868072489e-06,
      "loss": 1.5195,
      "step": 5
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 0.6655553579330444,
      "learning_rate": 9.68474862499881e-06,
      "loss": 1.5742,
      "step": 6
    },
    {
      "epoch": 0.1590909090909091,
      "grad_norm": 0.5706614255905151,
      "learning_rate": 9.548159976772593e-06,
      "loss": 1.4844,
      "step": 7
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.475175678730011,
      "learning_rate": 9.388394947836278e-06,
      "loss": 1.3945,
      "step": 8
    },
    {
      "epoch": 0.20454545454545456,
      "grad_norm": 0.3502136170864105,
      "learning_rate": 9.206267664155906e-06,
      "loss": 1.2715,
      "step": 9
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 0.3131449818611145,
      "learning_rate": 9.002706204621802e-06,
      "loss": 1.2505,
      "step": 10
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.31128987669944763,
      "learning_rate": 8.778747871771293e-06,
      "loss": 1.2871,
      "step": 11
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.27951738238334656,
      "learning_rate": 8.535533905932739e-06,
      "loss": 1.2998,
      "step": 12
    },
    {
      "epoch": 0.29545454545454547,
      "grad_norm": 0.27488085627555847,
      "learning_rate": 8.274303669726427e-06,
      "loss": 1.2715,
      "step": 13
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 0.22167572379112244,
      "learning_rate": 7.996388332556735e-06,
      "loss": 1.2021,
      "step": 14
    },
    {
      "epoch": 0.3409090909090909,
      "grad_norm": 0.20614755153656006,
      "learning_rate": 7.703204087277989e-06,
      "loss": 1.1504,
      "step": 15
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.20356248319149017,
      "learning_rate": 7.396244933600285e-06,
      "loss": 1.2002,
      "step": 16
    },
    {
      "epoch": 0.38636363636363635,
      "grad_norm": 0.21368511021137238,
      "learning_rate": 7.0770750650094335e-06,
      "loss": 1.2227,
      "step": 17
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 0.22877632081508636,
      "learning_rate": 6.747320897995493e-06,
      "loss": 1.2178,
      "step": 18
    },
    {
      "epoch": 0.4318181818181818,
      "grad_norm": 0.17466963827610016,
      "learning_rate": 6.408662784207149e-06,
      "loss": 1.1519,
      "step": 19
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.15983618795871735,
      "learning_rate": 6.062826447764883e-06,
      "loss": 1.1328,
      "step": 20
    },
    {
      "epoch": 0.4772727272727273,
      "grad_norm": 0.17516164481639862,
      "learning_rate": 5.711574191366427e-06,
      "loss": 1.1357,
      "step": 21
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.18316319584846497,
      "learning_rate": 5.356695915996162e-06,
      "loss": 1.1982,
      "step": 22
    },
    {
      "epoch": 0.5227272727272727,
      "grad_norm": 0.17309130728244781,
      "learning_rate": 5e-06,
      "loss": 1.1787,
      "step": 23
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.13374373316764832,
      "learning_rate": 4.643304084003839e-06,
      "loss": 1.1621,
      "step": 24
    },
    {
      "epoch": 0.5681818181818182,
      "grad_norm": 0.14121490716934204,
      "learning_rate": 4.2884258086335755e-06,
      "loss": 1.0938,
      "step": 25
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 0.11921057105064392,
      "learning_rate": 3.937173552235117e-06,
      "loss": 1.1211,
      "step": 26
    },
    {
      "epoch": 0.6136363636363636,
      "grad_norm": 0.12953969836235046,
      "learning_rate": 3.5913372157928515e-06,
      "loss": 1.1357,
      "step": 27
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 0.10501114279031754,
      "learning_rate": 3.252679102004509e-06,
      "loss": 1.0688,
      "step": 28
    },
    {
      "epoch": 0.6590909090909091,
      "grad_norm": 0.1202402114868164,
      "learning_rate": 2.9229249349905686e-06,
      "loss": 1.123,
      "step": 29
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 0.1425148844718933,
      "learning_rate": 2.603755066399718e-06,
      "loss": 1.1147,
      "step": 30
    },
    {
      "epoch": 0.7045454545454546,
      "grad_norm": 0.11402461677789688,
      "learning_rate": 2.296795912722014e-06,
      "loss": 1.0894,
      "step": 31
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.10801238566637039,
      "learning_rate": 2.0036116674432653e-06,
      "loss": 1.0737,
      "step": 32
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.12676717340946198,
      "learning_rate": 1.7256963302735752e-06,
      "loss": 1.1104,
      "step": 33
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 0.11957606673240662,
      "learning_rate": 1.4644660940672628e-06,
      "loss": 1.0967,
      "step": 34
    },
    {
      "epoch": 0.7954545454545454,
      "grad_norm": 0.11644243448972702,
      "learning_rate": 1.2212521282287093e-06,
      "loss": 1.126,
      "step": 35
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.15514206886291504,
      "learning_rate": 9.972937953781985e-07,
      "loss": 1.1709,
      "step": 36
    },
    {
      "epoch": 0.8409090909090909,
      "grad_norm": 0.1359109878540039,
      "learning_rate": 7.937323358440935e-07,
      "loss": 1.127,
      "step": 37
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 0.11309649050235748,
      "learning_rate": 6.116050521637218e-07,
      "loss": 1.1172,
      "step": 38
    },
    {
      "epoch": 0.8863636363636364,
      "grad_norm": 0.12017849832773209,
      "learning_rate": 4.5184002322740784e-07,
      "loss": 1.1143,
      "step": 39
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.11073319613933563,
      "learning_rate": 3.1525137500119207e-07,
      "loss": 1.1016,
      "step": 40
    },
    {
      "epoch": 0.9318181818181818,
      "grad_norm": 0.12839657068252563,
      "learning_rate": 2.0253513192751374e-07,
      "loss": 1.106,
      "step": 41
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 0.10681787133216858,
      "learning_rate": 1.1426567014420297e-07,
      "loss": 1.0947,
      "step": 42
    },
    {
      "epoch": 0.9772727272727273,
      "grad_norm": 0.14041878283023834,
      "learning_rate": 5.089279059533658e-08,
      "loss": 1.1616,
      "step": 43
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.10214513540267944,
      "learning_rate": 1.2739426948732426e-08,
      "loss": 1.0562,
      "step": 44
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.1954345703125,
      "eval_runtime": 4.2591,
      "eval_samples_per_second": 7.513,
      "eval_steps_per_second": 0.939,
      "step": 44
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 44,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 4.305898739387597e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}