{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 174,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08733624454148471,
      "grad_norm": 6.099521160125732,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.4051,
      "step": 5
    },
    {
      "epoch": 0.17467248908296942,
      "grad_norm": 7.150094032287598,
      "learning_rate": 9.992134075089085e-06,
      "loss": 0.4124,
      "step": 10
    },
    {
      "epoch": 0.26200873362445415,
      "grad_norm": 7.586390495300293,
      "learning_rate": 9.944154131125643e-06,
      "loss": 0.4349,
      "step": 15
    },
    {
      "epoch": 0.34934497816593885,
      "grad_norm": 5.689783096313477,
      "learning_rate": 9.852982837266955e-06,
      "loss": 0.4195,
      "step": 20
    },
    {
      "epoch": 0.4366812227074236,
      "grad_norm": 5.594226360321045,
      "learning_rate": 9.719416651541839e-06,
      "loss": 0.4551,
      "step": 25
    },
    {
      "epoch": 0.5240174672489083,
      "grad_norm": 5.31730842590332,
      "learning_rate": 9.544622387061055e-06,
      "loss": 0.4028,
      "step": 30
    },
    {
      "epoch": 0.611353711790393,
      "grad_norm": 6.336578845977783,
      "learning_rate": 9.330127018922195e-06,
      "loss": 0.482,
      "step": 35
    },
    {
      "epoch": 0.6986899563318777,
      "grad_norm": 5.558196067810059,
      "learning_rate": 9.077804344796302e-06,
      "loss": 0.477,
      "step": 40
    },
    {
      "epoch": 0.7860262008733624,
      "grad_norm": 6.426137924194336,
      "learning_rate": 8.789858615727266e-06,
      "loss": 0.4114,
      "step": 45
    },
    {
      "epoch": 0.8733624454148472,
      "grad_norm": 5.5606889724731445,
      "learning_rate": 8.46880528014271e-06,
      "loss": 0.4838,
      "step": 50
    },
    {
      "epoch": 0.9606986899563319,
      "grad_norm": 4.891933917999268,
      "learning_rate": 8.117449009293668e-06,
      "loss": 0.4448,
      "step": 55
    },
    {
      "epoch": 1.034934497816594,
      "grad_norm": 3.2774300575256348,
      "learning_rate": 7.738859196089358e-06,
      "loss": 0.2675,
      "step": 60
    },
    {
      "epoch": 1.1222707423580787,
      "grad_norm": 3.163228750228882,
      "learning_rate": 7.336343141365311e-06,
      "loss": 0.1811,
      "step": 65
    },
    {
      "epoch": 1.2096069868995634,
      "grad_norm": 5.830031871795654,
      "learning_rate": 6.913417161825449e-06,
      "loss": 0.1519,
      "step": 70
    },
    {
      "epoch": 1.296943231441048,
      "grad_norm": 5.245013236999512,
      "learning_rate": 6.473775872054522e-06,
      "loss": 0.1598,
      "step": 75
    },
    {
      "epoch": 1.3842794759825328,
      "grad_norm": 4.4215922355651855,
      "learning_rate": 6.0212599089484026e-06,
      "loss": 0.1512,
      "step": 80
    },
    {
      "epoch": 1.4716157205240175,
      "grad_norm": 6.280041217803955,
      "learning_rate": 5.559822380516539e-06,
      "loss": 0.1577,
      "step": 85
    },
    {
      "epoch": 1.5589519650655022,
      "grad_norm": 4.83260440826416,
      "learning_rate": 5.093494332154511e-06,
      "loss": 0.1561,
      "step": 90
    },
    {
      "epoch": 1.6462882096069869,
      "grad_norm": 3.9001753330230713,
      "learning_rate": 4.626349532067879e-06,
      "loss": 0.15,
      "step": 95
    },
    {
      "epoch": 1.7336244541484715,
      "grad_norm": 3.855449914932251,
      "learning_rate": 4.162468883476319e-06,
      "loss": 0.1732,
      "step": 100
    },
    {
      "epoch": 1.8209606986899565,
      "grad_norm": 3.9630279541015625,
      "learning_rate": 3.705904774487396e-06,
      "loss": 0.1395,
      "step": 105
    },
    {
      "epoch": 1.908296943231441,
      "grad_norm": 3.4962213039398193,
      "learning_rate": 3.2606456770738636e-06,
      "loss": 0.1395,
      "step": 110
    },
    {
      "epoch": 1.9956331877729259,
      "grad_norm": 4.331171989440918,
      "learning_rate": 2.83058130441221e-06,
      "loss": 0.1457,
      "step": 115
    },
    {
      "epoch": 2.069868995633188,
      "grad_norm": 1.9649221897125244,
      "learning_rate": 2.4194686309624664e-06,
      "loss": 0.0539,
      "step": 120
    },
    {
      "epoch": 2.1572052401746724,
      "grad_norm": 2.125267267227173,
      "learning_rate": 2.030899072132493e-06,
      "loss": 0.0614,
      "step": 125
    },
    {
      "epoch": 2.2445414847161573,
      "grad_norm": 2.2011775970458984,
      "learning_rate": 1.6682671102399806e-06,
      "loss": 0.0495,
      "step": 130
    },
    {
      "epoch": 2.331877729257642,
      "grad_norm": 2.0080509185791016,
      "learning_rate": 1.3347406408508695e-06,
      "loss": 0.0426,
      "step": 135
    },
    {
      "epoch": 2.4192139737991267,
      "grad_norm": 2.2091283798217773,
      "learning_rate": 1.0332332985438248e-06,
      "loss": 0.0523,
      "step": 140
    },
    {
      "epoch": 2.506550218340611,
      "grad_norm": 2.981034517288208,
      "learning_rate": 7.663790038585794e-07,
      "loss": 0.0519,
      "step": 145
    },
    {
      "epoch": 2.593886462882096,
      "grad_norm": 2.086867094039917,
      "learning_rate": 5.365089537819435e-07,
      "loss": 0.0438,
      "step": 150
    },
    {
      "epoch": 2.681222707423581,
      "grad_norm": 2.0733108520507812,
      "learning_rate": 3.4563125677897936e-07,
      "loss": 0.0442,
      "step": 155
    },
    {
      "epoch": 2.7685589519650655,
      "grad_norm": 1.9344326257705688,
      "learning_rate": 1.9541339027450256e-07,
      "loss": 0.0458,
      "step": 160
    },
    {
      "epoch": 2.85589519650655,
      "grad_norm": 1.9986166954040527,
      "learning_rate": 8.716763383355863e-08,
      "loss": 0.0437,
      "step": 165
    },
    {
      "epoch": 2.943231441048035,
      "grad_norm": 2.552715301513672,
      "learning_rate": 2.1839605294330935e-08,
      "loss": 0.0548,
      "step": 170
    }
  ],
  "logging_steps": 5,
  "max_steps": 174,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.323975476776796e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}