{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 95,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 64.44918823242188,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 5.9893,
      "step": 4
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 1.1460206508636475,
      "learning_rate": 3.888888888888889e-05,
      "loss": 1.7662,
      "step": 8
    },
    {
      "epoch": 0.25263157894736843,
      "grad_norm": 0.8948838710784912,
      "learning_rate": 6.111111111111112e-05,
      "loss": 0.8212,
      "step": 12
    },
    {
      "epoch": 0.3368421052631579,
      "grad_norm": 0.5042845606803894,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.533,
      "step": 16
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.5063032507896423,
      "learning_rate": 0.00010555555555555557,
      "loss": 0.425,
      "step": 20
    },
    {
      "epoch": 0.5052631578947369,
      "grad_norm": 0.4761255383491516,
      "learning_rate": 0.00012777777777777776,
      "loss": 0.3875,
      "step": 24
    },
    {
      "epoch": 0.5894736842105263,
      "grad_norm": 0.4021145701408386,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.3799,
      "step": 28
    },
    {
      "epoch": 0.6736842105263158,
      "grad_norm": 0.441383421421051,
      "learning_rate": 0.00017222222222222224,
      "loss": 0.3438,
      "step": 32
    },
    {
      "epoch": 0.7578947368421053,
      "grad_norm": 0.3923978805541992,
      "learning_rate": 0.00019444444444444446,
      "loss": 0.2952,
      "step": 36
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.39148256182670593,
      "learning_rate": 0.00019999007677495127,
      "loss": 0.2766,
      "step": 40
    },
    {
      "epoch": 0.9263157894736842,
      "grad_norm": 0.3753437101840973,
      "learning_rate": 0.0001999459775237086,
      "loss": 0.329,
      "step": 44
    },
    {
      "epoch": 1.0105263157894737,
      "grad_norm": 0.49228230118751526,
      "learning_rate": 0.00019986661520865405,
      "loss": 0.2808,
      "step": 48
    },
    {
      "epoch": 1.0947368421052632,
      "grad_norm": 0.3359147608280182,
      "learning_rate": 0.00019975201783049805,
      "loss": 0.2385,
      "step": 52
    },
    {
      "epoch": 1.1789473684210527,
      "grad_norm": 0.33956533670425415,
      "learning_rate": 0.00019960222582162976,
      "loss": 0.224,
      "step": 56
    },
    {
      "epoch": 1.263157894736842,
      "grad_norm": 0.29228124022483826,
      "learning_rate": 0.00019941729203185165,
      "loss": 0.2062,
      "step": 60
    },
    {
      "epoch": 1.3473684210526315,
      "grad_norm": 0.3463740944862366,
      "learning_rate": 0.00019919728170973296,
      "loss": 0.2335,
      "step": 64
    },
    {
      "epoch": 1.431578947368421,
      "grad_norm": 0.30409345030784607,
      "learning_rate": 0.00019894227247958845,
      "loss": 0.2242,
      "step": 68
    },
    {
      "epoch": 1.5157894736842106,
      "grad_norm": 0.3040483593940735,
      "learning_rate": 0.00019865235431409123,
      "loss": 0.1707,
      "step": 72
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.3167271614074707,
      "learning_rate": 0.00019832762950252813,
      "loss": 0.2288,
      "step": 76
    },
    {
      "epoch": 1.6842105263157894,
      "grad_norm": 0.4126874804496765,
      "learning_rate": 0.00019796821261471018,
      "loss": 0.202,
      "step": 80
    },
    {
      "epoch": 1.768421052631579,
      "grad_norm": 0.3122522830963135,
      "learning_rate": 0.00019757423046054968,
      "loss": 0.2209,
      "step": 84
    },
    {
      "epoch": 1.8526315789473684,
      "grad_norm": 0.348960280418396,
      "learning_rate": 0.00019714582204531918,
      "loss": 0.1551,
      "step": 88
    },
    {
      "epoch": 1.936842105263158,
      "grad_norm": 0.413482666015625,
      "learning_rate": 0.00019668313852060735,
      "loss": 0.1818,
      "step": 92
    }
  ],
  "logging_steps": 4,
  "max_steps": 705,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.812911896487526e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}