{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 7265,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06882312456985547,
      "grad_norm": 0.6455472111701965,
      "learning_rate": 0.00014969999999999998,
      "loss": 4.89012646484375,
      "step": 500
    },
    {
      "epoch": 0.13764624913971094,
      "grad_norm": 0.546249508857727,
      "learning_rate": 0.00029969999999999997,
      "loss": 2.893400146484375,
      "step": 1000
    },
    {
      "epoch": 0.20646937370956642,
      "grad_norm": 0.43270039558410645,
      "learning_rate": 0.00029532853869058343,
      "loss": 2.0761533203125,
      "step": 1500
    },
    {
      "epoch": 0.27529249827942187,
      "grad_norm": 0.37517938017845154,
      "learning_rate": 0.00028156901467649766,
      "loss": 1.810734619140625,
      "step": 2000
    },
    {
      "epoch": 0.3441156228492774,
      "grad_norm": 0.3215874433517456,
      "learning_rate": 0.0002595818572780397,
      "loss": 1.6727777099609376,
      "step": 2500
    },
    {
      "epoch": 0.41293874741913283,
      "grad_norm": 0.3056698441505432,
      "learning_rate": 0.00023074202754271595,
      "loss": 1.5861005859375,
      "step": 3000
    },
    {
      "epoch": 0.4817618719889883,
      "grad_norm": 0.3129520118236542,
      "learning_rate": 0.00019685301656235683,
      "loss": 1.52688525390625,
      "step": 3500
    },
    {
      "epoch": 0.5505849965588437,
      "grad_norm": 0.2816142439842224,
      "learning_rate": 0.00016003406463674675,
      "loss": 1.479068115234375,
      "step": 4000
    },
    {
      "epoch": 0.6194081211286993,
      "grad_norm": 0.27311035990715027,
      "learning_rate": 0.0001225876351444069,
      "loss": 1.440277587890625,
      "step": 4500
    },
    {
      "epoch": 0.6882312456985548,
      "grad_norm": 0.26458030939102173,
      "learning_rate": 8.685543060681822e-05,
      "loss": 1.4058232421875,
      "step": 5000
    },
    {
      "epoch": 0.7570543702684102,
      "grad_norm": 0.2703981101512909,
      "learning_rate": 5.5071954943262434e-05,
      "loss": 1.3814718017578125,
      "step": 5500
    },
    {
      "epoch": 0.8258774948382657,
      "grad_norm": 0.2578605115413666,
      "learning_rate": 2.9224779361777036e-05,
      "loss": 1.3585260009765625,
      "step": 6000
    },
    {
      "epoch": 0.8947006194081212,
      "grad_norm": 0.2610727846622467,
      "learning_rate": 1.0930250121614964e-05,
      "loss": 1.34341748046875,
      "step": 6500
    },
    {
      "epoch": 0.9635237439779766,
      "grad_norm": 0.2619054615497589,
      "learning_rate": 1.332410749269447e-06,
      "loss": 1.3385958251953125,
      "step": 7000
    }
  ],
  "logging_steps": 500,
  "max_steps": 7265,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 5.757369439129436e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}