{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.052328623757195186,
  "eval_steps": 3,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0020931449502878076,
      "grad_norm": 2.9366672039031982,
      "learning_rate": 2e-05,
      "loss": 5.1134,
      "step": 1
    },
    {
      "epoch": 0.0020931449502878076,
      "eval_loss": 1.3874133825302124,
      "eval_runtime": 28.3528,
      "eval_samples_per_second": 7.125,
      "eval_steps_per_second": 3.562,
      "step": 1
    },
    {
      "epoch": 0.004186289900575615,
      "grad_norm": 3.305058479309082,
      "learning_rate": 4e-05,
      "loss": 5.432,
      "step": 2
    },
    {
      "epoch": 0.006279434850863423,
      "grad_norm": 2.9360413551330566,
      "learning_rate": 6e-05,
      "loss": 5.7705,
      "step": 3
    },
    {
      "epoch": 0.006279434850863423,
      "eval_loss": 1.3774594068527222,
      "eval_runtime": 28.6485,
      "eval_samples_per_second": 7.051,
      "eval_steps_per_second": 3.525,
      "step": 3
    },
    {
      "epoch": 0.00837257980115123,
      "grad_norm": 3.4692842960357666,
      "learning_rate": 8e-05,
      "loss": 6.4354,
      "step": 4
    },
    {
      "epoch": 0.010465724751439037,
      "grad_norm": 3.079684019088745,
      "learning_rate": 0.0001,
      "loss": 4.955,
      "step": 5
    },
    {
      "epoch": 0.012558869701726845,
      "grad_norm": 3.631309986114502,
      "learning_rate": 9.938441702975689e-05,
      "loss": 4.4486,
      "step": 6
    },
    {
      "epoch": 0.012558869701726845,
      "eval_loss": 1.2356057167053223,
      "eval_runtime": 28.6368,
      "eval_samples_per_second": 7.054,
      "eval_steps_per_second": 3.527,
      "step": 6
    },
    {
      "epoch": 0.014652014652014652,
      "grad_norm": 4.206442356109619,
      "learning_rate": 9.755282581475769e-05,
      "loss": 4.5265,
      "step": 7
    },
    {
      "epoch": 0.01674515960230246,
      "grad_norm": 2.819859504699707,
      "learning_rate": 9.45503262094184e-05,
      "loss": 3.6465,
      "step": 8
    },
    {
      "epoch": 0.018838304552590265,
      "grad_norm": 3.166618824005127,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.6821,
      "step": 9
    },
    {
      "epoch": 0.018838304552590265,
      "eval_loss": 0.971888542175293,
      "eval_runtime": 28.6342,
      "eval_samples_per_second": 7.054,
      "eval_steps_per_second": 3.527,
      "step": 9
    },
    {
      "epoch": 0.020931449502878074,
      "grad_norm": 3.5012850761413574,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.6575,
      "step": 10
    },
    {
      "epoch": 0.023024594453165882,
      "grad_norm": 5.032680988311768,
      "learning_rate": 7.938926261462366e-05,
      "loss": 4.096,
      "step": 11
    },
    {
      "epoch": 0.02511773940345369,
      "grad_norm": 3.810659646987915,
      "learning_rate": 7.269952498697734e-05,
      "loss": 2.9131,
      "step": 12
    },
    {
      "epoch": 0.02511773940345369,
      "eval_loss": 0.7286272644996643,
      "eval_runtime": 28.6298,
      "eval_samples_per_second": 7.056,
      "eval_steps_per_second": 3.528,
      "step": 12
    },
    {
      "epoch": 0.027210884353741496,
      "grad_norm": 2.648770570755005,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.9433,
      "step": 13
    },
    {
      "epoch": 0.029304029304029304,
      "grad_norm": 2.9842631816864014,
      "learning_rate": 5.782172325201155e-05,
      "loss": 2.2262,
      "step": 14
    },
    {
      "epoch": 0.03139717425431711,
      "grad_norm": 3.5351529121398926,
      "learning_rate": 5e-05,
      "loss": 2.8287,
      "step": 15
    },
    {
      "epoch": 0.03139717425431711,
      "eval_loss": 0.5874171257019043,
      "eval_runtime": 28.604,
      "eval_samples_per_second": 7.062,
      "eval_steps_per_second": 3.531,
      "step": 15
    },
    {
      "epoch": 0.03349031920460492,
      "grad_norm": 2.774341344833374,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 2.1482,
      "step": 16
    },
    {
      "epoch": 0.035583464154892726,
      "grad_norm": 2.640618324279785,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.0841,
      "step": 17
    },
    {
      "epoch": 0.03767660910518053,
      "grad_norm": 3.8104114532470703,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 2.4072,
      "step": 18
    },
    {
      "epoch": 0.03767660910518053,
      "eval_loss": 0.510881245136261,
      "eval_runtime": 28.714,
      "eval_samples_per_second": 7.035,
      "eval_steps_per_second": 3.517,
      "step": 18
    },
    {
      "epoch": 0.03976975405546834,
      "grad_norm": 2.4819905757904053,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.8718,
      "step": 19
    },
    {
      "epoch": 0.04186289900575615,
      "grad_norm": 3.231020212173462,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.3639,
      "step": 20
    },
    {
      "epoch": 0.04395604395604396,
      "grad_norm": 2.7575583457946777,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.8185,
      "step": 21
    },
    {
      "epoch": 0.04395604395604396,
      "eval_loss": 0.4724537432193756,
      "eval_runtime": 28.7756,
      "eval_samples_per_second": 7.02,
      "eval_steps_per_second": 3.51,
      "step": 21
    },
    {
      "epoch": 0.046049188906331764,
      "grad_norm": 2.319027900695801,
      "learning_rate": 5.449673790581611e-06,
      "loss": 1.7463,
      "step": 22
    },
    {
      "epoch": 0.04814233385661957,
      "grad_norm": 3.020266056060791,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.9595,
      "step": 23
    },
    {
      "epoch": 0.05023547880690738,
      "grad_norm": 2.4685897827148438,
      "learning_rate": 6.15582970243117e-07,
      "loss": 1.7662,
      "step": 24
    },
    {
      "epoch": 0.05023547880690738,
      "eval_loss": 0.4614010155200958,
      "eval_runtime": 28.736,
      "eval_samples_per_second": 7.03,
      "eval_steps_per_second": 3.515,
      "step": 24
    },
    {
      "epoch": 0.052328623757195186,
      "grad_norm": 4.819024085998535,
      "learning_rate": 0.0,
      "loss": 2.0695,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8143746210201600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}