{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.442340791738382,
  "eval_steps": 5000,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1721170395869191,
      "grad_norm": 134.16664123535156,
      "learning_rate": 2.224770642201835e-06,
      "loss": 10.8697,
      "step": 100
    },
    {
      "epoch": 0.3442340791738382,
      "grad_norm": 69.6041259765625,
      "learning_rate": 4.5183486238532115e-06,
      "loss": 9.1125,
      "step": 200
    },
    {
      "epoch": 0.5163511187607573,
      "grad_norm": 103.4394760131836,
      "learning_rate": 6.8119266055045875e-06,
      "loss": 6.8873,
      "step": 300
    },
    {
      "epoch": 0.6884681583476764,
      "grad_norm": 32.237342834472656,
      "learning_rate": 9.08256880733945e-06,
      "loss": 3.1124,
      "step": 400
    },
    {
      "epoch": 0.8605851979345955,
      "grad_norm": 13.523033142089844,
      "learning_rate": 1.1376146788990828e-05,
      "loss": 1.0882,
      "step": 500
    },
    {
      "epoch": 1.0327022375215147,
      "grad_norm": 56.13002395629883,
      "learning_rate": 1.3669724770642203e-05,
      "loss": 0.869,
      "step": 600
    },
    {
      "epoch": 1.2048192771084336,
      "grad_norm": 4.41276741027832,
      "learning_rate": 1.5963302752293578e-05,
      "loss": 0.6952,
      "step": 700
    },
    {
      "epoch": 1.3769363166953528,
      "grad_norm": 1.8771318197250366,
      "learning_rate": 1.8256880733944955e-05,
      "loss": 0.5522,
      "step": 800
    },
    {
      "epoch": 1.549053356282272,
      "grad_norm": 5.131401062011719,
      "learning_rate": 1.9938798928981258e-05,
      "loss": 0.5184,
      "step": 900
    },
    {
      "epoch": 1.721170395869191,
      "grad_norm": 3.2520999908447266,
      "learning_rate": 1.9683794466403164e-05,
      "loss": 0.3996,
      "step": 1000
    },
    {
      "epoch": 1.8932874354561102,
      "grad_norm": 1.1916402578353882,
      "learning_rate": 1.9428790003825067e-05,
      "loss": 0.6316,
      "step": 1100
    },
    {
      "epoch": 2.0654044750430294,
      "grad_norm": 3.3565962314605713,
      "learning_rate": 1.9173785541246974e-05,
      "loss": 0.5352,
      "step": 1200
    },
    {
      "epoch": 2.2375215146299485,
      "grad_norm": 2.182133436203003,
      "learning_rate": 1.8918781078668877e-05,
      "loss": 0.3731,
      "step": 1300
    },
    {
      "epoch": 2.4096385542168672,
      "grad_norm": 3.537748098373413,
      "learning_rate": 1.8663776616090783e-05,
      "loss": 0.3376,
      "step": 1400
    },
    {
      "epoch": 2.581755593803787,
      "grad_norm": 2.066549777984619,
      "learning_rate": 1.840877215351269e-05,
      "loss": 0.597,
      "step": 1500
    },
    {
      "epoch": 2.7538726333907055,
      "grad_norm": 2.867453098297119,
      "learning_rate": 1.8153767690934592e-05,
      "loss": 0.5737,
      "step": 1600
    },
    {
      "epoch": 2.9259896729776247,
      "grad_norm": 0.8096536993980408,
      "learning_rate": 1.7898763228356495e-05,
      "loss": 0.7107,
      "step": 1700
    },
    {
      "epoch": 3.098106712564544,
      "grad_norm": 5.293230056762695,
      "learning_rate": 1.7643758765778402e-05,
      "loss": 0.4356,
      "step": 1800
    },
    {
      "epoch": 3.270223752151463,
      "grad_norm": 2.1939845085144043,
      "learning_rate": 1.7388754303200308e-05,
      "loss": 0.5581,
      "step": 1900
    },
    {
      "epoch": 3.442340791738382,
      "grad_norm": 2.1973116397857666,
      "learning_rate": 1.713374984062221e-05,
      "loss": 0.2012,
      "step": 2000
    }
  ],
  "logging_steps": 100,
  "max_steps": 8715,
  "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": 0.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}