{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 0,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "grad_norm": 0.8126010894775391,
      "learning_rate": 0.0001,
      "loss": 2.5195,
      "step": 1
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.6318886876106262,
      "learning_rate": 9.96057350657239e-05,
      "loss": 2.4746,
      "step": 2
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.6070905327796936,
      "learning_rate": 9.842915805643155e-05,
      "loss": 2.104,
      "step": 3
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.8297808766365051,
      "learning_rate": 9.648882429441257e-05,
      "loss": 1.71,
      "step": 4
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.542759358882904,
      "learning_rate": 9.381533400219318e-05,
      "loss": 1.6958,
      "step": 5
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.5389617681503296,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.6782,
      "step": 6
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.41869819164276123,
      "learning_rate": 8.644843137107059e-05,
      "loss": 1.4639,
      "step": 7
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.40936756134033203,
      "learning_rate": 8.18711994874345e-05,
      "loss": 1.4502,
      "step": 8
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.38802680373191833,
      "learning_rate": 7.679133974894983e-05,
      "loss": 1.5938,
      "step": 9
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.38405802845954895,
      "learning_rate": 7.128896457825364e-05,
      "loss": 1.353,
      "step": 10
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.4222624897956848,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.2231,
      "step": 11
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.3813856244087219,
      "learning_rate": 5.9369065729286245e-05,
      "loss": 1.2881,
      "step": 12
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.35140013694763184,
      "learning_rate": 5.313952597646568e-05,
      "loss": 1.2698,
      "step": 13
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.38519105315208435,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 1.1603,
      "step": 14
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.449541300535202,
      "learning_rate": 4.063093427071376e-05,
      "loss": 1.4028,
      "step": 15
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.4203754663467407,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.1782,
      "step": 16
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.34995225071907043,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 1.1171,
      "step": 17
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.3616626262664795,
      "learning_rate": 2.3208660251050158e-05,
      "loss": 1.1107,
      "step": 18
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.3145160973072052,
      "learning_rate": 1.8128800512565513e-05,
      "loss": 1.0703,
      "step": 19
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.373938649892807,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 0.9536,
      "step": 20
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.3546522557735443,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.069,
      "step": 21
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.33890411257743835,
      "learning_rate": 6.184665997806832e-06,
      "loss": 1.1539,
      "step": 22
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.4365558624267578,
      "learning_rate": 3.511175705587433e-06,
      "loss": 1.3467,
      "step": 23
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.3421511948108673,
      "learning_rate": 1.5708419435684462e-06,
      "loss": 1.3057,
      "step": 24
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.36208391189575195,
      "learning_rate": 3.9426493427611177e-07,
      "loss": 1.3625,
      "step": 25
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4596252322824192.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}