{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.987452948557089,
  "eval_steps": 500,
  "global_step": 198,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "grad_norm": 0.07030480355024338,
      "learning_rate": 0.0002,
      "loss": 1.3367,
      "step": 10
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.07384990900754929,
      "learning_rate": 0.0002,
      "loss": 0.9811,
      "step": 20
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.046176519244909286,
      "learning_rate": 0.0002,
      "loss": 1.1,
      "step": 30
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.04807846248149872,
      "learning_rate": 0.0002,
      "loss": 1.0853,
      "step": 40
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.07028425484895706,
      "learning_rate": 0.0002,
      "loss": 0.8954,
      "step": 50
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.04952001944184303,
      "learning_rate": 0.0002,
      "loss": 1.1859,
      "step": 60
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.06458909064531326,
      "learning_rate": 0.0002,
      "loss": 0.8935,
      "step": 70
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.051869411021471024,
      "learning_rate": 0.0002,
      "loss": 1.0834,
      "step": 80
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.07632376253604889,
      "learning_rate": 0.0002,
      "loss": 1.0116,
      "step": 90
    },
    {
      "epoch": 0.99,
      "eval_loss": 1.043639063835144,
      "eval_runtime": 14.9586,
      "eval_samples_per_second": 6.685,
      "eval_steps_per_second": 0.267,
      "step": 99
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.07128819078207016,
      "learning_rate": 0.0002,
      "loss": 0.8683,
      "step": 100
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.04056414216756821,
      "learning_rate": 0.0002,
      "loss": 1.1677,
      "step": 110
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.06517702341079712,
      "learning_rate": 0.0002,
      "loss": 0.8393,
      "step": 120
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.05269412696361542,
      "learning_rate": 0.0002,
      "loss": 1.0144,
      "step": 130
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.06893514841794968,
      "learning_rate": 0.0002,
      "loss": 1.0169,
      "step": 140
    },
    {
      "epoch": 1.51,
      "grad_norm": 0.047447849065065384,
      "learning_rate": 0.0002,
      "loss": 0.798,
      "step": 150
    },
    {
      "epoch": 1.61,
      "grad_norm": 0.04566727951169014,
      "learning_rate": 0.0002,
      "loss": 1.1378,
      "step": 160
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.08533580601215363,
      "learning_rate": 0.0002,
      "loss": 0.8075,
      "step": 170
    },
    {
      "epoch": 1.81,
      "grad_norm": 0.04863196611404419,
      "learning_rate": 0.0002,
      "loss": 1.0397,
      "step": 180
    },
    {
      "epoch": 1.91,
      "grad_norm": 0.06892246007919312,
      "learning_rate": 0.0002,
      "loss": 0.9698,
      "step": 190
    },
    {
      "epoch": 1.99,
      "eval_loss": 1.031528115272522,
      "eval_runtime": 4.0808,
      "eval_samples_per_second": 24.505,
      "eval_steps_per_second": 0.98,
      "step": 198
    }
  ],
  "logging_steps": 10,
  "max_steps": 198,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 250,
  "total_flos": 6.906134738176573e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}