{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17,
      "grad_norm": 1.5211801688193387,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 2.2228,
      "step": 1
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.8768693619108074,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.2578,
      "step": 5
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.319545030593872,
      "eval_runtime": 0.9291,
      "eval_samples_per_second": 10.763,
      "eval_steps_per_second": 1.076,
      "step": 6
    },
    {
      "epoch": 1.67,
      "grad_norm": 0.9129027161633834,
      "learning_rate": 1.973044870579824e-05,
      "loss": 2.1177,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.1448023319244385,
      "eval_runtime": 0.9069,
      "eval_samples_per_second": 11.027,
      "eval_steps_per_second": 1.103,
      "step": 12
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.5540888575509927,
      "learning_rate": 1.866025403784439e-05,
      "loss": 2.0262,
      "step": 15
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.141737699508667,
      "eval_runtime": 0.8967,
      "eval_samples_per_second": 11.153,
      "eval_steps_per_second": 1.115,
      "step": 18
    },
    {
      "epoch": 3.33,
      "grad_norm": 0.43326943938341794,
      "learning_rate": 1.686241637868734e-05,
      "loss": 1.9422,
      "step": 20
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.2227349281311035,
      "eval_runtime": 0.8973,
      "eval_samples_per_second": 11.145,
      "eval_steps_per_second": 1.114,
      "step": 24
    },
    {
      "epoch": 4.17,
      "grad_norm": 0.41719894619516695,
      "learning_rate": 1.4487991802004625e-05,
      "loss": 1.852,
      "step": 25
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.3971456461863458,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 1.7786,
      "step": 30
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.33267879486084,
      "eval_runtime": 0.8833,
      "eval_samples_per_second": 11.321,
      "eval_steps_per_second": 1.132,
      "step": 30
    },
    {
      "epoch": 5.83,
      "grad_norm": 0.4197975929814425,
      "learning_rate": 8.839070858747697e-06,
      "loss": 1.7224,
      "step": 35
    },
    {
      "epoch": 6.0,
      "eval_loss": 2.420168876647949,
      "eval_runtime": 0.8954,
      "eval_samples_per_second": 11.168,
      "eval_steps_per_second": 1.117,
      "step": 36
    },
    {
      "epoch": 6.67,
      "grad_norm": 0.7910417276022704,
      "learning_rate": 6.039202339608432e-06,
      "loss": 1.684,
      "step": 40
    },
    {
      "epoch": 7.0,
      "eval_loss": 2.469820022583008,
      "eval_runtime": 0.8921,
      "eval_samples_per_second": 11.209,
      "eval_steps_per_second": 1.121,
      "step": 42
    },
    {
      "epoch": 7.5,
      "grad_norm": 0.4695825804003894,
      "learning_rate": 3.5721239031346067e-06,
      "loss": 1.6434,
      "step": 45
    },
    {
      "epoch": 8.0,
      "eval_loss": 2.496063470840454,
      "eval_runtime": 0.9014,
      "eval_samples_per_second": 11.094,
      "eval_steps_per_second": 1.109,
      "step": 48
    },
    {
      "epoch": 8.33,
      "grad_norm": 0.7286746951597681,
      "learning_rate": 1.6451218858706374e-06,
      "loss": 1.616,
      "step": 50
    },
    {
      "epoch": 9.0,
      "eval_loss": 2.5094497203826904,
      "eval_runtime": 0.8925,
      "eval_samples_per_second": 11.204,
      "eval_steps_per_second": 1.12,
      "step": 54
    },
    {
      "epoch": 9.17,
      "grad_norm": 0.3635222353269055,
      "learning_rate": 4.2010487684511105e-07,
      "loss": 1.617,
      "step": 55
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.36655481676051715,
      "learning_rate": 0.0,
      "loss": 1.6183,
      "step": 60
    },
    {
      "epoch": 10.0,
      "eval_loss": 2.5095889568328857,
      "eval_runtime": 0.8858,
      "eval_samples_per_second": 11.29,
      "eval_steps_per_second": 1.129,
      "step": 60
    },
    {
      "epoch": 10.0,
      "step": 60,
      "total_flos": 45177687244800.0,
      "train_loss": 1.8223904927571615,
      "train_runtime": 196.3016,
      "train_samples_per_second": 34.182,
      "train_steps_per_second": 0.306
    }
  ],
  "logging_steps": 5,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 1000000000,
  "total_flos": 45177687244800.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}