{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 67,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07462686567164178,
      "grad_norm": 7.644242763519287,
      "learning_rate": 1.1428571428571429e-05,
      "loss": 0.6495,
      "step": 5
    },
    {
      "epoch": 0.14925373134328357,
      "grad_norm": 0.7384787201881409,
      "learning_rate": 1.9945218953682736e-05,
      "loss": 0.0995,
      "step": 10
    },
    {
      "epoch": 0.22388059701492538,
      "grad_norm": 1.0291929244995117,
      "learning_rate": 1.9335804264972018e-05,
      "loss": 0.1127,
      "step": 15
    },
    {
      "epoch": 0.29850746268656714,
      "grad_norm": 0.27176418900489807,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.0891,
      "step": 20
    },
    {
      "epoch": 0.373134328358209,
      "grad_norm": 0.37762412428855896,
      "learning_rate": 1.6293203910498375e-05,
      "loss": 0.0879,
      "step": 25
    },
    {
      "epoch": 0.44776119402985076,
      "grad_norm": 0.5627060532569885,
      "learning_rate": 1.4067366430758004e-05,
      "loss": 0.0868,
      "step": 30
    },
    {
      "epoch": 0.5223880597014925,
      "grad_norm": 0.6722306609153748,
      "learning_rate": 1.156434465040231e-05,
      "loss": 0.0879,
      "step": 35
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 0.10741408169269562,
      "learning_rate": 8.954715367323468e-06,
      "loss": 0.0875,
      "step": 40
    },
    {
      "epoch": 0.6716417910447762,
      "grad_norm": 0.5069949626922607,
      "learning_rate": 6.4163205045469975e-06,
      "loss": 0.0875,
      "step": 45
    },
    {
      "epoch": 0.746268656716418,
      "grad_norm": 0.4571477770805359,
      "learning_rate": 4.12214747707527e-06,
      "loss": 0.0975,
      "step": 50
    },
    {
      "epoch": 0.8208955223880597,
      "grad_norm": 0.3213711977005005,
      "learning_rate": 2.2285403854302912e-06,
      "loss": 0.0866,
      "step": 55
    },
    {
      "epoch": 0.8955223880597015,
      "grad_norm": 0.26998254656791687,
      "learning_rate": 8.645454235739903e-07,
      "loss": 0.0863,
      "step": 60
    },
    {
      "epoch": 0.9701492537313433,
      "grad_norm": 0.26005396246910095,
      "learning_rate": 1.231165940486234e-07,
      "loss": 0.0864,
      "step": 65
    },
    {
      "epoch": 1.0,
      "step": 67,
      "total_flos": 2.587386052566057e+17,
      "train_loss": 0.13282569709108838,
      "train_runtime": 1624.0926,
      "train_samples_per_second": 2.629,
      "train_steps_per_second": 0.041
    }
  ],
  "logging_steps": 5,
  "max_steps": 67,
  "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": 2.587386052566057e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}