{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 66,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 0.12914219144102593,
      "learning_rate": 1.4285714285714286e-06,
      "loss": 0.5151,
      "step": 1
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 0.10294084507814112,
      "learning_rate": 7.1428571428571436e-06,
      "loss": 0.5084,
      "step": 5
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 0.11430775946527363,
      "learning_rate": 9.936341773606723e-06,
      "loss": 0.5085,
      "step": 10
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.08588455579355678,
      "learning_rate": 9.553173864274567e-06,
      "loss": 0.4765,
      "step": 15
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.0720040180861239,
      "learning_rate": 8.849169917149532e-06,
      "loss": 0.4394,
      "step": 20
    },
    {
      "epoch": 0.7575757575757576,
      "grad_norm": 0.06453236041824466,
      "learning_rate": 7.873937051072037e-06,
      "loss": 0.4322,
      "step": 25
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.05882814905970625,
      "learning_rate": 6.6961943305901515e-06,
      "loss": 0.4058,
      "step": 30
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.42501434683799744,
      "eval_runtime": 28.7091,
      "eval_samples_per_second": 18.984,
      "eval_steps_per_second": 4.772,
      "step": 33
    },
    {
      "epoch": 1.0606060606060606,
      "grad_norm": 0.056958863910414055,
      "learning_rate": 5.398930527765416e-06,
      "loss": 0.3821,
      "step": 35
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 0.05279260475294177,
      "learning_rate": 4.073556379564429e-06,
      "loss": 0.3697,
      "step": 40
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.05128712340945032,
      "learning_rate": 2.8134633977057236e-06,
      "loss": 0.3503,
      "step": 45
    },
    {
      "epoch": 1.5151515151515151,
      "grad_norm": 0.060058454006873215,
      "learning_rate": 1.7074431046748075e-06,
      "loss": 0.3674,
      "step": 50
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.0483607238694913,
      "learning_rate": 8.334304045874248e-07,
      "loss": 0.3641,
      "step": 55
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.05802115776370139,
      "learning_rate": 2.530119576580936e-07,
      "loss": 0.3614,
      "step": 60
    },
    {
      "epoch": 1.9696969696969697,
      "grad_norm": 0.05938652178950297,
      "learning_rate": 7.0865216161902785e-09,
      "loss": 0.3696,
      "step": 65
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.4221389591693878,
      "eval_runtime": 28.8226,
      "eval_samples_per_second": 18.909,
      "eval_steps_per_second": 4.753,
      "step": 66
    },
    {
      "epoch": 2.0,
      "step": 66,
      "total_flos": 1.681359576886149e+17,
      "train_loss": 0.4086628511096492,
      "train_runtime": 982.585,
      "train_samples_per_second": 3.224,
      "train_steps_per_second": 0.067
    }
  ],
  "logging_steps": 5,
  "max_steps": 66,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.681359576886149e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}