{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.028169014084507,
  "eval_steps": 54,
  "global_step": 432,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "grad_norm": 2.008165121078491,
      "learning_rate": 1.267605633802817e-05,
      "loss": 1.1495,
      "step": 54
    },
    {
      "epoch": 0.25,
      "eval_loss": 1.0628074407577515,
      "eval_runtime": 52.6632,
      "eval_samples_per_second": 4.272,
      "eval_steps_per_second": 1.082,
      "step": 54
    },
    {
      "epoch": 0.51,
      "grad_norm": 2.2451069355010986,
      "learning_rate": 2.535211267605634e-05,
      "loss": 1.0005,
      "step": 108
    },
    {
      "epoch": 0.51,
      "eval_loss": 0.887832522392273,
      "eval_runtime": 52.6576,
      "eval_samples_per_second": 4.273,
      "eval_steps_per_second": 1.082,
      "step": 108
    },
    {
      "epoch": 0.76,
      "grad_norm": 2.4120945930480957,
      "learning_rate": 3.802816901408451e-05,
      "loss": 0.9146,
      "step": 162
    },
    {
      "epoch": 0.76,
      "eval_loss": 0.8374146819114685,
      "eval_runtime": 52.6723,
      "eval_samples_per_second": 4.272,
      "eval_steps_per_second": 1.082,
      "step": 162
    },
    {
      "epoch": 1.01,
      "grad_norm": 2.2599024772644043,
      "learning_rate": 4.992175273865415e-05,
      "loss": 0.8691,
      "step": 216
    },
    {
      "epoch": 1.01,
      "eval_loss": 0.8268610239028931,
      "eval_runtime": 52.6677,
      "eval_samples_per_second": 4.272,
      "eval_steps_per_second": 1.082,
      "step": 216
    },
    {
      "epoch": 1.27,
      "grad_norm": 1.9341202974319458,
      "learning_rate": 4.85133020344288e-05,
      "loss": 0.7958,
      "step": 270
    },
    {
      "epoch": 1.27,
      "eval_loss": 0.8176680207252502,
      "eval_runtime": 52.6631,
      "eval_samples_per_second": 4.272,
      "eval_steps_per_second": 1.082,
      "step": 270
    },
    {
      "epoch": 1.52,
      "grad_norm": 2.5440659523010254,
      "learning_rate": 4.710485133020345e-05,
      "loss": 0.8392,
      "step": 324
    },
    {
      "epoch": 1.52,
      "eval_loss": 0.8067876696586609,
      "eval_runtime": 52.6929,
      "eval_samples_per_second": 4.27,
      "eval_steps_per_second": 1.082,
      "step": 324
    },
    {
      "epoch": 1.77,
      "grad_norm": 2.226438045501709,
      "learning_rate": 4.569640062597809e-05,
      "loss": 0.8403,
      "step": 378
    },
    {
      "epoch": 1.77,
      "eval_loss": 0.8039852380752563,
      "eval_runtime": 52.681,
      "eval_samples_per_second": 4.271,
      "eval_steps_per_second": 1.082,
      "step": 378
    },
    {
      "epoch": 2.03,
      "grad_norm": 2.865570306777954,
      "learning_rate": 4.428794992175274e-05,
      "loss": 0.7955,
      "step": 432
    },
    {
      "epoch": 2.03,
      "eval_loss": 0.7987839579582214,
      "eval_runtime": 52.6893,
      "eval_samples_per_second": 4.27,
      "eval_steps_per_second": 1.082,
      "step": 432
    }
  ],
  "logging_steps": 54,
  "max_steps": 2130,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 54,
  "total_flos": 3.019243546873037e+16,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}