{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "global_step": 25150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 1.900198807157058e-05,
      "loss": 3.4819,
      "step": 2515
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.2373175621032715,
      "eval_runtime": 310.738,
      "eval_samples_per_second": 28.777,
      "eval_steps_per_second": 1.799,
      "step": 2515
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.8002385685884693e-05,
      "loss": 2.1965,
      "step": 5030
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.8015460968017578,
      "eval_runtime": 310.6652,
      "eval_samples_per_second": 28.783,
      "eval_steps_per_second": 1.799,
      "step": 5030
    },
    {
      "epoch": 3.0,
      "learning_rate": 1.700278330019881e-05,
      "loss": 1.8805,
      "step": 7545
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.5936048030853271,
      "eval_runtime": 310.3586,
      "eval_samples_per_second": 28.812,
      "eval_steps_per_second": 1.801,
      "step": 7545
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.6003180914512923e-05,
      "loss": 1.6926,
      "step": 10060
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.451478362083435,
      "eval_runtime": 310.2705,
      "eval_samples_per_second": 28.82,
      "eval_steps_per_second": 1.802,
      "step": 10060
    },
    {
      "epoch": 5.0,
      "learning_rate": 1.500357852882704e-05,
      "loss": 1.5731,
      "step": 12575
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.3821080923080444,
      "eval_runtime": 310.2193,
      "eval_samples_per_second": 28.825,
      "eval_steps_per_second": 1.802,
      "step": 12575
    },
    {
      "epoch": 6.0,
      "learning_rate": 1.4003976143141154e-05,
      "loss": 1.4862,
      "step": 15090
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.3046475648880005,
      "eval_runtime": 310.6594,
      "eval_samples_per_second": 28.784,
      "eval_steps_per_second": 1.799,
      "step": 15090
    },
    {
      "epoch": 7.0,
      "learning_rate": 1.3003976143141155e-05,
      "loss": 1.4197,
      "step": 17605
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.253291368484497,
      "eval_runtime": 310.6843,
      "eval_samples_per_second": 28.782,
      "eval_steps_per_second": 1.799,
      "step": 17605
    },
    {
      "epoch": 8.0,
      "learning_rate": 1.20051689860835e-05,
      "loss": 1.368,
      "step": 20120
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.221903920173645,
      "eval_runtime": 310.6521,
      "eval_samples_per_second": 28.785,
      "eval_steps_per_second": 1.799,
      "step": 20120
    },
    {
      "epoch": 9.0,
      "learning_rate": 1.10051689860835e-05,
      "loss": 1.3235,
      "step": 22635
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.1836310625076294,
      "eval_runtime": 310.7209,
      "eval_samples_per_second": 28.778,
      "eval_steps_per_second": 1.799,
      "step": 22635
    },
    {
      "epoch": 10.0,
      "learning_rate": 1.00051689860835e-05,
      "loss": 1.2855,
      "step": 25150
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.1522128582000732,
      "eval_runtime": 310.7087,
      "eval_samples_per_second": 28.779,
      "eval_steps_per_second": 1.799,
      "step": 25150
    }
  ],
  "max_steps": 50300,
  "num_train_epochs": 20,
  "total_flos": 5.301609303112704e+16,
  "trial_name": null,
  "trial_params": null
}