{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9048750141386721,
  "eval_steps": 100,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09048750141386722,
      "eval_accuracy": 0.16714730898859703,
      "eval_loss": 4.686699867248535,
      "eval_runtime": 125.2427,
      "eval_samples_per_second": 7.218,
      "eval_steps_per_second": 7.218,
      "step": 100
    },
    {
      "epoch": 0.18097500282773443,
      "eval_accuracy": 0.25826880194607743,
      "eval_loss": 3.9017727375030518,
      "eval_runtime": 125.5606,
      "eval_samples_per_second": 7.2,
      "eval_steps_per_second": 7.2,
      "step": 200
    },
    {
      "epoch": 0.2714625042416016,
      "eval_accuracy": 0.29766981254599767,
      "eval_loss": 3.5929646492004395,
      "eval_runtime": 125.5573,
      "eval_samples_per_second": 7.2,
      "eval_steps_per_second": 7.2,
      "step": 300
    },
    {
      "epoch": 0.36195000565546886,
      "eval_accuracy": 0.3236774609630093,
      "eval_loss": 3.4225211143493652,
      "eval_runtime": 125.7379,
      "eval_samples_per_second": 7.19,
      "eval_steps_per_second": 7.19,
      "step": 400
    },
    {
      "epoch": 0.45243750706933605,
      "grad_norm": 4.40625,
      "learning_rate": 4.7737556561085976e-05,
      "loss": 4.0632,
      "step": 500
    },
    {
      "epoch": 0.45243750706933605,
      "eval_accuracy": 0.3405748527595257,
      "eval_loss": 3.307744026184082,
      "eval_runtime": 125.5713,
      "eval_samples_per_second": 7.199,
      "eval_steps_per_second": 7.199,
      "step": 500
    },
    {
      "epoch": 0.5429250084832032,
      "eval_accuracy": 0.354706238577747,
      "eval_loss": 3.21340012550354,
      "eval_runtime": 125.6117,
      "eval_samples_per_second": 7.197,
      "eval_steps_per_second": 7.197,
      "step": 600
    },
    {
      "epoch": 0.6334125098970704,
      "eval_accuracy": 0.3676221206998826,
      "eval_loss": 3.127941608428955,
      "eval_runtime": 125.646,
      "eval_samples_per_second": 7.195,
      "eval_steps_per_second": 7.195,
      "step": 700
    },
    {
      "epoch": 0.7239000113109377,
      "eval_accuracy": 0.377770033996102,
      "eval_loss": 3.0699830055236816,
      "eval_runtime": 125.238,
      "eval_samples_per_second": 7.218,
      "eval_steps_per_second": 7.218,
      "step": 800
    },
    {
      "epoch": 0.8143875127248049,
      "eval_accuracy": 0.3878323087639568,
      "eval_loss": 2.992367744445801,
      "eval_runtime": 126.0865,
      "eval_samples_per_second": 7.17,
      "eval_steps_per_second": 7.17,
      "step": 900
    },
    {
      "epoch": 0.9048750141386721,
      "grad_norm": 5.15625,
      "learning_rate": 4.547511312217195e-05,
      "loss": 3.0582,
      "step": 1000
    },
    {
      "epoch": 0.9048750141386721,
      "eval_accuracy": 0.3950470582191688,
      "eval_loss": 2.9669389724731445,
      "eval_runtime": 125.9784,
      "eval_samples_per_second": 7.176,
      "eval_steps_per_second": 7.176,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 11050,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 200,
  "total_flos": 7.41888088866816e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}