{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6535947712418301,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "grad_norm": 0.9236222505569458,
      "learning_rate": 1.893939393939394e-05,
      "loss": 2.0583,
      "step": 25
    },
    {
      "epoch": 0.16,
      "eval_loss": 0.787165105342865,
      "eval_runtime": 305.3412,
      "eval_samples_per_second": 1.002,
      "eval_steps_per_second": 0.128,
      "step": 25
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.8654550909996033,
      "learning_rate": 1.2626262626262628e-05,
      "loss": 0.6304,
      "step": 50
    },
    {
      "epoch": 0.33,
      "eval_loss": 0.5769306421279907,
      "eval_runtime": 305.7633,
      "eval_samples_per_second": 1.001,
      "eval_steps_per_second": 0.128,
      "step": 50
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.9291855096817017,
      "learning_rate": 6.313131313131314e-06,
      "loss": 0.5751,
      "step": 75
    },
    {
      "epoch": 0.49,
      "eval_loss": 0.5544592142105103,
      "eval_runtime": 305.0351,
      "eval_samples_per_second": 1.003,
      "eval_steps_per_second": 0.128,
      "step": 75
    },
    {
      "epoch": 0.65,
      "grad_norm": 2.704556465148926,
      "learning_rate": 0.0,
      "loss": 0.5249,
      "step": 100
    },
    {
      "epoch": 0.65,
      "eval_loss": 0.5473166108131409,
      "eval_runtime": 304.9674,
      "eval_samples_per_second": 1.003,
      "eval_steps_per_second": 0.128,
      "step": 100
    }
  ],
  "logging_steps": 25,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "total_flos": 7973920309248000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}