{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 38.0,
  "eval_steps": 5,
  "global_step": 114,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.67,
      "learning_rate": 2.9999177540482684e-05,
      "loss": 2.6576,
      "step": 2
    },
    {
      "epoch": 1.33,
      "learning_rate": 2.9996710252122685e-05,
      "loss": 2.1353,
      "step": 4
    },
    {
      "epoch": 2.0,
      "learning_rate": 2.9992598405485974e-05,
      "loss": 1.8307,
      "step": 6
    },
    {
      "epoch": 2.67,
      "learning_rate": 2.9986842451482876e-05,
      "loss": 1.5685,
      "step": 8
    },
    {
      "epoch": 3.33,
      "learning_rate": 2.9979443021318607e-05,
      "loss": 1.3489,
      "step": 10
    },
    {
      "epoch": 4.0,
      "learning_rate": 2.9970400926424075e-05,
      "loss": 1.1757,
      "step": 12
    },
    {
      "epoch": 4.67,
      "learning_rate": 2.995971715836687e-05,
      "loss": 1.0709,
      "step": 14
    },
    {
      "epoch": 5.33,
      "learning_rate": 2.9947392888742566e-05,
      "loss": 1.0194,
      "step": 16
    },
    {
      "epoch": 6.0,
      "learning_rate": 2.9933429469046202e-05,
      "loss": 0.9694,
      "step": 18
    },
    {
      "epoch": 6.67,
      "learning_rate": 2.99178284305241e-05,
      "loss": 0.9486,
      "step": 20
    },
    {
      "epoch": 7.33,
      "learning_rate": 2.9900591484005944e-05,
      "loss": 0.9138,
      "step": 22
    },
    {
      "epoch": 8.0,
      "learning_rate": 2.988172051971717e-05,
      "loss": 0.8702,
      "step": 24
    },
    {
      "epoch": 8.67,
      "learning_rate": 2.9861217607071655e-05,
      "loss": 0.8556,
      "step": 26
    },
    {
      "epoch": 9.33,
      "learning_rate": 2.983908499444483e-05,
      "loss": 0.7949,
      "step": 28
    },
    {
      "epoch": 10.0,
      "learning_rate": 2.981532510892707e-05,
      "loss": 0.785,
      "step": 30
    },
    {
      "epoch": 10.67,
      "learning_rate": 2.9789940556057574e-05,
      "loss": 0.7599,
      "step": 32
    },
    {
      "epoch": 11.33,
      "learning_rate": 2.9762934119538628e-05,
      "loss": 0.7527,
      "step": 34
    },
    {
      "epoch": 12.0,
      "learning_rate": 2.9734308760930333e-05,
      "loss": 0.7187,
      "step": 36
    },
    {
      "epoch": 12.67,
      "learning_rate": 2.9704067619325828e-05,
      "loss": 0.7241,
      "step": 38
    },
    {
      "epoch": 13.33,
      "learning_rate": 2.9672214011007087e-05,
      "loss": 0.7075,
      "step": 40
    },
    {
      "epoch": 14.0,
      "learning_rate": 2.9638751429081213e-05,
      "loss": 0.6973,
      "step": 42
    },
    {
      "epoch": 14.67,
      "learning_rate": 2.9603683543097406e-05,
      "loss": 0.6908,
      "step": 44
    },
    {
      "epoch": 15.33,
      "learning_rate": 2.9567014198644542e-05,
      "loss": 0.6889,
      "step": 46
    },
    {
      "epoch": 16.0,
      "learning_rate": 2.9528747416929467e-05,
      "loss": 0.675,
      "step": 48
    },
    {
      "epoch": 16.67,
      "learning_rate": 2.9488887394336025e-05,
      "loss": 0.6694,
      "step": 50
    },
    {
      "epoch": 17.33,
      "learning_rate": 2.9447438501964873e-05,
      "loss": 0.6485,
      "step": 52
    },
    {
      "epoch": 18.0,
      "learning_rate": 2.9404405285154146e-05,
      "loss": 0.6777,
      "step": 54
    },
    {
      "epoch": 18.67,
      "learning_rate": 2.9359792462981007e-05,
      "loss": 0.66,
      "step": 56
    },
    {
      "epoch": 19.33,
      "learning_rate": 2.9313604927744153e-05,
      "loss": 0.6394,
      "step": 58
    },
    {
      "epoch": 20.0,
      "learning_rate": 2.9265847744427305e-05,
      "loss": 0.6423,
      "step": 60
    },
    {
      "epoch": 20.67,
      "learning_rate": 2.9216526150143788e-05,
      "loss": 0.6443,
      "step": 62
    },
    {
      "epoch": 21.33,
      "learning_rate": 2.9165645553562215e-05,
      "loss": 0.6145,
      "step": 64
    },
    {
      "epoch": 22.0,
      "learning_rate": 2.9113211534313385e-05,
      "loss": 0.6314,
      "step": 66
    },
    {
      "epoch": 22.67,
      "learning_rate": 2.9059229842378373e-05,
      "loss": 0.6284,
      "step": 68
    },
    {
      "epoch": 23.33,
      "learning_rate": 2.9003706397458025e-05,
      "loss": 0.6108,
      "step": 70
    },
    {
      "epoch": 24.0,
      "learning_rate": 2.894664728832377e-05,
      "loss": 0.6019,
      "step": 72
    },
    {
      "epoch": 24.67,
      "learning_rate": 2.8888058772149923e-05,
      "loss": 0.5989,
      "step": 74
    },
    {
      "epoch": 25.33,
      "learning_rate": 2.8827947273827508e-05,
      "loss": 0.6023,
      "step": 76
    },
    {
      "epoch": 26.0,
      "learning_rate": 2.8766319385259717e-05,
      "loss": 0.59,
      "step": 78
    },
    {
      "epoch": 26.67,
      "learning_rate": 2.8703181864639013e-05,
      "loss": 0.5903,
      "step": 80
    },
    {
      "epoch": 27.33,
      "learning_rate": 2.863854163570603e-05,
      "loss": 0.5749,
      "step": 82
    },
    {
      "epoch": 28.0,
      "learning_rate": 2.8572405786990293e-05,
      "loss": 0.5749,
      "step": 84
    },
    {
      "epoch": 28.67,
      "learning_rate": 2.8504781571032906e-05,
      "loss": 0.5567,
      "step": 86
    },
    {
      "epoch": 29.33,
      "learning_rate": 2.8435676403591193e-05,
      "loss": 0.5799,
      "step": 88
    },
    {
      "epoch": 30.0,
      "learning_rate": 2.8365097862825516e-05,
      "loss": 0.5487,
      "step": 90
    },
    {
      "epoch": 30.67,
      "learning_rate": 2.829305368846822e-05,
      "loss": 0.5397,
      "step": 92
    },
    {
      "epoch": 31.33,
      "learning_rate": 2.821955178097488e-05,
      "loss": 0.5498,
      "step": 94
    },
    {
      "epoch": 32.0,
      "learning_rate": 2.8144600200657953e-05,
      "loss": 0.5355,
      "step": 96
    },
    {
      "epoch": 32.67,
      "learning_rate": 2.8068207166802843e-05,
      "loss": 0.5364,
      "step": 98
    },
    {
      "epoch": 33.33,
      "learning_rate": 2.7990381056766583e-05,
      "loss": 0.5156,
      "step": 100
    },
    {
      "epoch": 34.0,
      "learning_rate": 2.7911130405059155e-05,
      "loss": 0.5018,
      "step": 102
    },
    {
      "epoch": 34.67,
      "learning_rate": 2.78304639024076e-05,
      "loss": 0.4921,
      "step": 104
    },
    {
      "epoch": 35.33,
      "learning_rate": 2.774839039480296e-05,
      "loss": 0.5089,
      "step": 106
    },
    {
      "epoch": 36.0,
      "learning_rate": 2.7664918882530227e-05,
      "loss": 0.4716,
      "step": 108
    },
    {
      "epoch": 36.67,
      "learning_rate": 2.7580058519181363e-05,
      "loss": 0.4648,
      "step": 110
    },
    {
      "epoch": 37.33,
      "learning_rate": 2.7493818610651493e-05,
      "loss": 0.4686,
      "step": 112
    },
    {
      "epoch": 38.0,
      "learning_rate": 2.7406208614118427e-05,
      "loss": 0.4419,
      "step": 114
    }
  ],
  "logging_steps": 2,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 200,
  "save_steps": 500,
  "total_flos": 6230274358640640.0,
  "train_batch_size": 52,
  "trial_name": null,
  "trial_params": null
}