{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.620408163265306,
  "eval_steps": 200,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16326530612244897,
      "grad_norm": 0.6756201386451721,
      "learning_rate": 0.0001981178176898239,
      "loss": 0.770789909362793,
      "step": 10
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": 0.6545600295066833,
      "learning_rate": 0.00018687117365181512,
      "loss": 0.7264016151428223,
      "step": 20
    },
    {
      "epoch": 0.4897959183673469,
      "grad_norm": 0.683688223361969,
      "learning_rate": 0.00016659152250116812,
      "loss": 0.7400761127471924,
      "step": 30
    },
    {
      "epoch": 0.6530612244897959,
      "grad_norm": 0.47568151354789734,
      "learning_rate": 0.00013938757562492873,
      "loss": 0.7011314392089844,
      "step": 40
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 0.42000776529312134,
      "learning_rate": 0.00010808804403614043,
      "loss": 0.672628116607666,
      "step": 50
    },
    {
      "epoch": 0.9795918367346939,
      "grad_norm": 0.4876711070537567,
      "learning_rate": 7.594750436337467e-05,
      "loss": 0.5931291103363037,
      "step": 60
    },
    {
      "epoch": 1.1306122448979592,
      "grad_norm": 0.5444473624229431,
      "learning_rate": 4.630798263510162e-05,
      "loss": 0.6527483463287354,
      "step": 70
    },
    {
      "epoch": 1.2938775510204081,
      "grad_norm": 0.6376090049743652,
      "learning_rate": 2.2251444932035094e-05,
      "loss": 0.576920461654663,
      "step": 80
    },
    {
      "epoch": 1.457142857142857,
      "grad_norm": 0.541858971118927,
      "learning_rate": 6.2793294993656494e-06,
      "loss": 0.5700631141662598,
      "step": 90
    },
    {
      "epoch": 1.620408163265306,
      "grad_norm": 0.4305003583431244,
      "learning_rate": 5.2443095448506674e-08,
      "loss": 0.5232778549194336,
      "step": 100
    },
    {
      "epoch": 1.620408163265306,
      "eval_loss": 0.8235033750534058,
      "eval_runtime": 0.6803,
      "eval_samples_per_second": 29.398,
      "eval_steps_per_second": 7.349,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 100,
  "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": 3287268790345728.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}