{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 1000,
  "global_step": 144,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06944444444444445,
      "grad_norm": 8.71909236907959,
      "learning_rate": 1e-06,
      "loss": 2.6593,
      "step": 5
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 8.853459358215332,
      "learning_rate": 1e-06,
      "loss": 2.4766,
      "step": 10
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 6.577568054199219,
      "learning_rate": 1e-06,
      "loss": 2.495,
      "step": 15
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 8.3203706741333,
      "learning_rate": 1e-06,
      "loss": 2.6105,
      "step": 20
    },
    {
      "epoch": 0.3472222222222222,
      "grad_norm": 7.732483863830566,
      "learning_rate": 1e-06,
      "loss": 2.4744,
      "step": 25
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 6.6942548751831055,
      "learning_rate": 1e-06,
      "loss": 2.5163,
      "step": 30
    },
    {
      "epoch": 0.4861111111111111,
      "grad_norm": 5.781284809112549,
      "learning_rate": 1e-06,
      "loss": 2.3854,
      "step": 35
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 7.311328887939453,
      "learning_rate": 1e-06,
      "loss": 2.4442,
      "step": 40
    },
    {
      "epoch": 0.625,
      "grad_norm": 6.254249572753906,
      "learning_rate": 1e-06,
      "loss": 2.2468,
      "step": 45
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 7.6778669357299805,
      "learning_rate": 1e-06,
      "loss": 2.2565,
      "step": 50
    },
    {
      "epoch": 0.7638888888888888,
      "grad_norm": 7.495645523071289,
      "learning_rate": 1e-06,
      "loss": 2.4391,
      "step": 55
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 5.458991527557373,
      "learning_rate": 1e-06,
      "loss": 2.2362,
      "step": 60
    },
    {
      "epoch": 0.9027777777777778,
      "grad_norm": 5.659170627593994,
      "learning_rate": 1e-06,
      "loss": 2.2188,
      "step": 65
    },
    {
      "epoch": 0.9722222222222222,
      "grad_norm": 4.8217997550964355,
      "learning_rate": 1e-06,
      "loss": 2.154,
      "step": 70
    },
    {
      "epoch": 1.0416666666666667,
      "grad_norm": 6.693627834320068,
      "learning_rate": 1e-06,
      "loss": 2.1182,
      "step": 75
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 6.67255973815918,
      "learning_rate": 1e-06,
      "loss": 2.1879,
      "step": 80
    },
    {
      "epoch": 1.1805555555555556,
      "grad_norm": 4.831326007843018,
      "learning_rate": 1e-06,
      "loss": 2.1077,
      "step": 85
    },
    {
      "epoch": 1.25,
      "grad_norm": 4.830414295196533,
      "learning_rate": 1e-06,
      "loss": 2.026,
      "step": 90
    },
    {
      "epoch": 1.3194444444444444,
      "grad_norm": 5.039080619812012,
      "learning_rate": 1e-06,
      "loss": 2.0585,
      "step": 95
    },
    {
      "epoch": 1.3888888888888888,
      "grad_norm": 5.749475002288818,
      "learning_rate": 1e-06,
      "loss": 2.0486,
      "step": 100
    },
    {
      "epoch": 1.4583333333333333,
      "grad_norm": 5.0571770668029785,
      "learning_rate": 1e-06,
      "loss": 1.9616,
      "step": 105
    },
    {
      "epoch": 1.5277777777777777,
      "grad_norm": 4.597809314727783,
      "learning_rate": 1e-06,
      "loss": 1.9063,
      "step": 110
    },
    {
      "epoch": 1.5972222222222223,
      "grad_norm": 5.453224182128906,
      "learning_rate": 1e-06,
      "loss": 2.1802,
      "step": 115
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 4.519564628601074,
      "learning_rate": 1e-06,
      "loss": 2.2049,
      "step": 120
    },
    {
      "epoch": 1.7361111111111112,
      "grad_norm": 4.976806163787842,
      "learning_rate": 1e-06,
      "loss": 1.8881,
      "step": 125
    },
    {
      "epoch": 1.8055555555555556,
      "grad_norm": 4.543058395385742,
      "learning_rate": 1e-06,
      "loss": 2.0673,
      "step": 130
    },
    {
      "epoch": 1.875,
      "grad_norm": 4.89597225189209,
      "learning_rate": 1e-06,
      "loss": 2.0158,
      "step": 135
    },
    {
      "epoch": 1.9444444444444444,
      "grad_norm": 4.95186185836792,
      "learning_rate": 1e-06,
      "loss": 2.0052,
      "step": 140
    },
    {
      "epoch": 2.0,
      "step": 144,
      "total_flos": 9.601343958286336e+16,
      "train_loss": 2.2213990655210285,
      "train_runtime": 2501.8045,
      "train_samples_per_second": 0.921,
      "train_steps_per_second": 0.058
    }
  ],
  "logging_steps": 5,
  "max_steps": 144,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 200,
  "total_flos": 9.601343958286336e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}