{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 1000,
  "global_step": 72,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06944444444444445,
      "grad_norm": 4.683212757110596,
      "learning_rate": 1e-06,
      "loss": 2.5448,
      "step": 5
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 4.721557140350342,
      "learning_rate": 1e-06,
      "loss": 2.4235,
      "step": 10
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 3.7502753734588623,
      "learning_rate": 1e-06,
      "loss": 2.5413,
      "step": 15
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 4.788341045379639,
      "learning_rate": 1e-06,
      "loss": 2.7545,
      "step": 20
    },
    {
      "epoch": 0.3472222222222222,
      "grad_norm": 4.027582168579102,
      "learning_rate": 1e-06,
      "loss": 2.398,
      "step": 25
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 4.083437442779541,
      "learning_rate": 1e-06,
      "loss": 2.737,
      "step": 30
    },
    {
      "epoch": 0.4861111111111111,
      "grad_norm": 3.840348720550537,
      "learning_rate": 1e-06,
      "loss": 2.6366,
      "step": 35
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 3.376926898956299,
      "learning_rate": 1e-06,
      "loss": 2.5638,
      "step": 40
    },
    {
      "epoch": 0.625,
      "grad_norm": 3.656587600708008,
      "learning_rate": 1e-06,
      "loss": 2.7568,
      "step": 45
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 2.5398614406585693,
      "learning_rate": 1e-06,
      "loss": 2.3856,
      "step": 50
    },
    {
      "epoch": 0.7638888888888888,
      "grad_norm": 2.253296136856079,
      "learning_rate": 1e-06,
      "loss": 2.268,
      "step": 55
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 2.464299201965332,
      "learning_rate": 1e-06,
      "loss": 2.45,
      "step": 60
    },
    {
      "epoch": 0.9027777777777778,
      "grad_norm": 2.9303369522094727,
      "learning_rate": 1e-06,
      "loss": 2.5548,
      "step": 65
    },
    {
      "epoch": 0.9722222222222222,
      "grad_norm": 1.658677339553833,
      "learning_rate": 1e-06,
      "loss": 2.3566,
      "step": 70
    },
    {
      "epoch": 1.0,
      "step": 72,
      "total_flos": 4.988916731582874e+16,
      "train_loss": 2.5252017312579684,
      "train_runtime": 672.6439,
      "train_samples_per_second": 1.713,
      "train_steps_per_second": 0.107
    }
  ],
  "logging_steps": 5,
  "max_steps": 72,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.988916731582874e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}