{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004340748779164406,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004340748779164406,
      "grad_norm": 161.049560546875,
      "learning_rate": 2e-05,
      "loss": 31.1973,
      "step": 1
    },
    {
      "epoch": 0.0004340748779164406,
      "eval_loss": 7.57180118560791,
      "eval_runtime": 94.7027,
      "eval_samples_per_second": 10.243,
      "eval_steps_per_second": 5.121,
      "step": 1
    },
    {
      "epoch": 0.0008681497558328812,
      "grad_norm": 175.77069091796875,
      "learning_rate": 4e-05,
      "loss": 29.6467,
      "step": 2
    },
    {
      "epoch": 0.0013022246337493217,
      "grad_norm": 159.03341674804688,
      "learning_rate": 6e-05,
      "loss": 31.4228,
      "step": 3
    },
    {
      "epoch": 0.0013022246337493217,
      "eval_loss": 6.619510173797607,
      "eval_runtime": 98.1983,
      "eval_samples_per_second": 9.878,
      "eval_steps_per_second": 4.939,
      "step": 3
    },
    {
      "epoch": 0.0017362995116657625,
      "grad_norm": 200.6622772216797,
      "learning_rate": 8e-05,
      "loss": 29.5694,
      "step": 4
    },
    {
      "epoch": 0.002170374389582203,
      "grad_norm": 101.65010070800781,
      "learning_rate": 0.0001,
      "loss": 20.2307,
      "step": 5
    },
    {
      "epoch": 0.0026044492674986435,
      "grad_norm": 113.74677276611328,
      "learning_rate": 0.00012,
      "loss": 19.303,
      "step": 6
    },
    {
      "epoch": 0.0026044492674986435,
      "eval_loss": 4.280592441558838,
      "eval_runtime": 99.4947,
      "eval_samples_per_second": 9.749,
      "eval_steps_per_second": 4.875,
      "step": 6
    },
    {
      "epoch": 0.003038524145415084,
      "grad_norm": 79.8565444946289,
      "learning_rate": 0.00014,
      "loss": 15.9631,
      "step": 7
    },
    {
      "epoch": 0.003472599023331525,
      "grad_norm": 56.37056350708008,
      "learning_rate": 0.00016,
      "loss": 13.9295,
      "step": 8
    },
    {
      "epoch": 0.003906673901247965,
      "grad_norm": 60.9976692199707,
      "learning_rate": 0.00018,
      "loss": 12.8817,
      "step": 9
    },
    {
      "epoch": 0.003906673901247965,
      "eval_loss": 2.358410120010376,
      "eval_runtime": 99.4254,
      "eval_samples_per_second": 9.756,
      "eval_steps_per_second": 4.878,
      "step": 9
    },
    {
      "epoch": 0.004340748779164406,
      "grad_norm": 60.41130065917969,
      "learning_rate": 0.0002,
      "loss": 10.0958,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1752671799214080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}