{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.31330774653403304,
  "eval_steps": 100,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "grad_norm": 7.659268856048584,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.3919,
      "step": 100
    },
    {
      "epoch": 0.03,
      "eval_loss": 1.1893327236175537,
      "eval_runtime": 192.797,
      "eval_samples_per_second": 5.187,
      "eval_steps_per_second": 5.187,
      "step": 100
    },
    {
      "epoch": 0.06,
      "grad_norm": 3.593693971633911,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.7649,
      "step": 200
    },
    {
      "epoch": 0.06,
      "eval_loss": 0.37141919136047363,
      "eval_runtime": 193.0277,
      "eval_samples_per_second": 5.181,
      "eval_steps_per_second": 5.181,
      "step": 200
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.2718026638031006,
      "learning_rate": 1.2e-05,
      "loss": 0.2492,
      "step": 300
    },
    {
      "epoch": 0.09,
      "eval_loss": 0.1235867515206337,
      "eval_runtime": 192.4574,
      "eval_samples_per_second": 5.196,
      "eval_steps_per_second": 5.196,
      "step": 300
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.3505817651748657,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.1111,
      "step": 400
    },
    {
      "epoch": 0.13,
      "eval_loss": 0.06019064038991928,
      "eval_runtime": 193.0151,
      "eval_samples_per_second": 5.181,
      "eval_steps_per_second": 5.181,
      "step": 400
    },
    {
      "epoch": 0.16,
      "grad_norm": 2.2099411487579346,
      "learning_rate": 2e-05,
      "loss": 0.1213,
      "step": 500
    },
    {
      "epoch": 0.16,
      "eval_loss": 0.05992453545331955,
      "eval_runtime": 193.5019,
      "eval_samples_per_second": 5.168,
      "eval_steps_per_second": 5.168,
      "step": 500
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.006523499730974436,
      "learning_rate": 1.9555555555555557e-05,
      "loss": 0.1161,
      "step": 600
    },
    {
      "epoch": 0.19,
      "eval_loss": 0.03172233700752258,
      "eval_runtime": 192.8437,
      "eval_samples_per_second": 5.186,
      "eval_steps_per_second": 5.186,
      "step": 600
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.0743604227900505,
      "learning_rate": 1.9111111111111113e-05,
      "loss": 0.0853,
      "step": 700
    },
    {
      "epoch": 0.22,
      "eval_loss": 0.03372843191027641,
      "eval_runtime": 193.2798,
      "eval_samples_per_second": 5.174,
      "eval_steps_per_second": 5.174,
      "step": 700
    },
    {
      "epoch": 0.25,
      "grad_norm": 2.5127480030059814,
      "learning_rate": 1.866666666666667e-05,
      "loss": 0.0801,
      "step": 800
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.02089008316397667,
      "eval_runtime": 193.1941,
      "eval_samples_per_second": 5.176,
      "eval_steps_per_second": 5.176,
      "step": 800
    },
    {
      "epoch": 0.28,
      "grad_norm": 2.219334125518799,
      "learning_rate": 1.8222222222222224e-05,
      "loss": 0.0619,
      "step": 900
    },
    {
      "epoch": 0.28,
      "eval_loss": 0.03212675824761391,
      "eval_runtime": 192.8222,
      "eval_samples_per_second": 5.186,
      "eval_steps_per_second": 5.186,
      "step": 900
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.01359077449887991,
      "learning_rate": 1.7777777777777777e-05,
      "loss": 0.0707,
      "step": 1000
    },
    {
      "epoch": 0.31,
      "eval_loss": 0.0244381632655859,
      "eval_runtime": 192.3716,
      "eval_samples_per_second": 5.198,
      "eval_steps_per_second": 5.198,
      "step": 1000
    }
  ],
  "logging_steps": 100,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 1000,
  "total_flos": 1.6102125993984e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}