{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8456659619450317,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.042283298097251586,
      "grad_norm": 1.2008394002914429,
      "learning_rate": 4.9975392245612254e-05,
      "loss": 4.1473,
      "num_input_tokens_seen": 68384,
      "step": 5
    },
    {
      "epoch": 0.08456659619450317,
      "grad_norm": 1.1565380096435547,
      "learning_rate": 4.9901617425775067e-05,
      "loss": 4.021,
      "num_input_tokens_seen": 128224,
      "step": 10
    },
    {
      "epoch": 0.12684989429175475,
      "grad_norm": 0.972896158695221,
      "learning_rate": 4.9778820775100185e-05,
      "loss": 3.8212,
      "num_input_tokens_seen": 197760,
      "step": 15
    },
    {
      "epoch": 0.16913319238900634,
      "grad_norm": 1.0641047954559326,
      "learning_rate": 4.9607244033573156e-05,
      "loss": 3.7653,
      "num_input_tokens_seen": 262832,
      "step": 20
    },
    {
      "epoch": 0.21141649048625794,
      "grad_norm": 1.0994701385498047,
      "learning_rate": 4.93872249706591e-05,
      "loss": 3.7434,
      "num_input_tokens_seen": 333472,
      "step": 25
    },
    {
      "epoch": 0.2536997885835095,
      "grad_norm": 1.193864107131958,
      "learning_rate": 4.91191967203629e-05,
      "loss": 3.5488,
      "num_input_tokens_seen": 393616,
      "step": 30
    },
    {
      "epoch": 0.2959830866807611,
      "grad_norm": 1.0215297937393188,
      "learning_rate": 4.8803686928552736e-05,
      "loss": 3.5732,
      "num_input_tokens_seen": 458240,
      "step": 35
    },
    {
      "epoch": 0.3382663847780127,
      "grad_norm": 1.312198519706726,
      "learning_rate": 4.84413167142257e-05,
      "loss": 3.7108,
      "num_input_tokens_seen": 524576,
      "step": 40
    },
    {
      "epoch": 0.38054968287526425,
      "grad_norm": 1.3579617738723755,
      "learning_rate": 4.803279944676032e-05,
      "loss": 3.6871,
      "num_input_tokens_seen": 591856,
      "step": 45
    },
    {
      "epoch": 0.42283298097251587,
      "grad_norm": 1.4524191617965698,
      "learning_rate": 4.7578939341563095e-05,
      "loss": 3.286,
      "num_input_tokens_seen": 655648,
      "step": 50
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 1.248831033706665,
      "learning_rate": 4.70806298768736e-05,
      "loss": 3.5377,
      "num_input_tokens_seen": 721280,
      "step": 55
    },
    {
      "epoch": 0.507399577167019,
      "grad_norm": 1.2427473068237305,
      "learning_rate": 4.653885203484515e-05,
      "loss": 3.56,
      "num_input_tokens_seen": 784688,
      "step": 60
    },
    {
      "epoch": 0.5496828752642706,
      "grad_norm": 1.323653221130371,
      "learning_rate": 4.595467237036329e-05,
      "loss": 3.4937,
      "num_input_tokens_seen": 850848,
      "step": 65
    },
    {
      "epoch": 0.5919661733615222,
      "grad_norm": 1.3730229139328003,
      "learning_rate": 4.532924091140417e-05,
      "loss": 3.3823,
      "num_input_tokens_seen": 912480,
      "step": 70
    },
    {
      "epoch": 0.6342494714587738,
      "grad_norm": 1.5328903198242188,
      "learning_rate": 4.466378889506607e-05,
      "loss": 3.3798,
      "num_input_tokens_seen": 978448,
      "step": 75
    },
    {
      "epoch": 0.6765327695560254,
      "grad_norm": 1.4153543710708618,
      "learning_rate": 4.395962634373097e-05,
      "loss": 3.3044,
      "num_input_tokens_seen": 1041280,
      "step": 80
    },
    {
      "epoch": 0.718816067653277,
      "grad_norm": 1.6301600933074951,
      "learning_rate": 4.3218139486127854e-05,
      "loss": 3.3661,
      "num_input_tokens_seen": 1102224,
      "step": 85
    },
    {
      "epoch": 0.7610993657505285,
      "grad_norm": 1.6634522676467896,
      "learning_rate": 4.2440788028374624e-05,
      "loss": 3.3829,
      "num_input_tokens_seen": 1166576,
      "step": 90
    },
    {
      "epoch": 0.8033826638477801,
      "grad_norm": 1.4539167881011963,
      "learning_rate": 4.1629102280370904e-05,
      "loss": 3.2241,
      "num_input_tokens_seen": 1230096,
      "step": 95
    },
    {
      "epoch": 0.8456659619450317,
      "grad_norm": 1.453364372253418,
      "learning_rate": 4.0784680143198836e-05,
      "loss": 3.0931,
      "num_input_tokens_seen": 1297968,
      "step": 100
    }
  ],
  "logging_steps": 5,
  "max_steps": 354,
  "num_input_tokens_seen": 1297968,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5457586224840704e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}