{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0221130221130221,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02620802620802621,
      "grad_norm": 0.688605546951294,
      "learning_rate": 5e-05,
      "loss": 1.9615,
      "step": 1
    },
    {
      "epoch": 0.02620802620802621,
      "eval_loss": 1.9379749298095703,
      "eval_runtime": 6.8873,
      "eval_samples_per_second": 37.315,
      "eval_steps_per_second": 9.438,
      "step": 1
    },
    {
      "epoch": 0.05241605241605242,
      "grad_norm": 0.7276808023452759,
      "learning_rate": 0.0001,
      "loss": 1.9459,
      "step": 2
    },
    {
      "epoch": 0.07862407862407862,
      "grad_norm": 0.7033953666687012,
      "learning_rate": 9.981987442712633e-05,
      "loss": 1.9077,
      "step": 3
    },
    {
      "epoch": 0.10483210483210484,
      "grad_norm": 0.719717264175415,
      "learning_rate": 9.928079551738543e-05,
      "loss": 1.9109,
      "step": 4
    },
    {
      "epoch": 0.13104013104013104,
      "grad_norm": 0.6515451669692993,
      "learning_rate": 9.838664734667495e-05,
      "loss": 1.8254,
      "step": 5
    },
    {
      "epoch": 0.15724815724815724,
      "grad_norm": 0.6293128728866577,
      "learning_rate": 9.714387227305422e-05,
      "loss": 1.7722,
      "step": 6
    },
    {
      "epoch": 0.18345618345618345,
      "grad_norm": 0.5616139769554138,
      "learning_rate": 9.55614245194068e-05,
      "loss": 1.7974,
      "step": 7
    },
    {
      "epoch": 0.20966420966420968,
      "grad_norm": 0.6011109948158264,
      "learning_rate": 9.365070565805941e-05,
      "loss": 1.7045,
      "step": 8
    },
    {
      "epoch": 0.23587223587223588,
      "grad_norm": 0.6134763956069946,
      "learning_rate": 9.142548246219212e-05,
      "loss": 1.7578,
      "step": 9
    },
    {
      "epoch": 0.2620802620802621,
      "grad_norm": 0.6061597466468811,
      "learning_rate": 8.890178771592199e-05,
      "loss": 1.7537,
      "step": 10
    },
    {
      "epoch": 0.2620802620802621,
      "eval_loss": 1.690554141998291,
      "eval_runtime": 6.9618,
      "eval_samples_per_second": 36.916,
      "eval_steps_per_second": 9.337,
      "step": 10
    },
    {
      "epoch": 0.2882882882882883,
      "grad_norm": 0.5569241642951965,
      "learning_rate": 8.609780469772623e-05,
      "loss": 1.6436,
      "step": 11
    },
    {
      "epoch": 0.3144963144963145,
      "grad_norm": 0.5158886313438416,
      "learning_rate": 8.303373616950408e-05,
      "loss": 1.6523,
      "step": 12
    },
    {
      "epoch": 0.3407043407043407,
      "grad_norm": 0.4968787729740143,
      "learning_rate": 7.973165881521434e-05,
      "loss": 1.6673,
      "step": 13
    },
    {
      "epoch": 0.3669123669123669,
      "grad_norm": 0.49128782749176025,
      "learning_rate": 7.621536417786159e-05,
      "loss": 1.6519,
      "step": 14
    },
    {
      "epoch": 0.3931203931203931,
      "grad_norm": 0.493300199508667,
      "learning_rate": 7.251018724088367e-05,
      "loss": 1.624,
      "step": 15
    },
    {
      "epoch": 0.41932841932841936,
      "grad_norm": 0.5251982808113098,
      "learning_rate": 6.864282388901544e-05,
      "loss": 1.6108,
      "step": 16
    },
    {
      "epoch": 0.44553644553644556,
      "grad_norm": 0.4884173274040222,
      "learning_rate": 6.464113856382752e-05,
      "loss": 1.6367,
      "step": 17
    },
    {
      "epoch": 0.47174447174447176,
      "grad_norm": 0.5205239653587341,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 1.6079,
      "step": 18
    },
    {
      "epoch": 0.49795249795249796,
      "grad_norm": 0.5160295963287354,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 1.6298,
      "step": 19
    },
    {
      "epoch": 0.5241605241605242,
      "grad_norm": 0.46167778968811035,
      "learning_rate": 5.212206015980742e-05,
      "loss": 1.7101,
      "step": 20
    },
    {
      "epoch": 0.5241605241605242,
      "eval_loss": 1.6339422464370728,
      "eval_runtime": 6.9719,
      "eval_samples_per_second": 36.862,
      "eval_steps_per_second": 9.323,
      "step": 20
    },
    {
      "epoch": 0.5503685503685504,
      "grad_norm": 0.4809012711048126,
      "learning_rate": 4.78779398401926e-05,
      "loss": 1.6745,
      "step": 21
    },
    {
      "epoch": 0.5765765765765766,
      "grad_norm": 0.44002801179885864,
      "learning_rate": 4.364910901265606e-05,
      "loss": 1.5675,
      "step": 22
    },
    {
      "epoch": 0.6027846027846028,
      "grad_norm": 0.4592677652835846,
      "learning_rate": 3.94660365002137e-05,
      "loss": 1.7446,
      "step": 23
    },
    {
      "epoch": 0.628992628992629,
      "grad_norm": 0.4685349762439728,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 1.6143,
      "step": 24
    },
    {
      "epoch": 0.6552006552006552,
      "grad_norm": 0.46893665194511414,
      "learning_rate": 3.135717611098458e-05,
      "loss": 1.6969,
      "step": 25
    },
    {
      "epoch": 0.6814086814086814,
      "grad_norm": 0.4547032415866852,
      "learning_rate": 2.748981275911633e-05,
      "loss": 1.6562,
      "step": 26
    },
    {
      "epoch": 0.7076167076167076,
      "grad_norm": 0.46321848034858704,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 1.6516,
      "step": 27
    },
    {
      "epoch": 0.7338247338247338,
      "grad_norm": 0.453426718711853,
      "learning_rate": 2.026834118478567e-05,
      "loss": 1.5961,
      "step": 28
    },
    {
      "epoch": 0.76003276003276,
      "grad_norm": 0.4333644211292267,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 1.6134,
      "step": 29
    },
    {
      "epoch": 0.7862407862407862,
      "grad_norm": 0.4507792592048645,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 1.5558,
      "step": 30
    },
    {
      "epoch": 0.7862407862407862,
      "eval_loss": 1.6152641773223877,
      "eval_runtime": 6.9374,
      "eval_samples_per_second": 37.045,
      "eval_steps_per_second": 9.369,
      "step": 30
    },
    {
      "epoch": 0.8124488124488124,
      "grad_norm": 0.4604407548904419,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 1.6154,
      "step": 31
    },
    {
      "epoch": 0.8386568386568387,
      "grad_norm": 0.4262702763080597,
      "learning_rate": 8.574517537807897e-06,
      "loss": 1.6072,
      "step": 32
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 0.452141135931015,
      "learning_rate": 6.349294341940593e-06,
      "loss": 1.6484,
      "step": 33
    },
    {
      "epoch": 0.8910728910728911,
      "grad_norm": 0.45040103793144226,
      "learning_rate": 4.43857548059321e-06,
      "loss": 1.6131,
      "step": 34
    },
    {
      "epoch": 0.9172809172809173,
      "grad_norm": 0.43721693754196167,
      "learning_rate": 2.85612772694579e-06,
      "loss": 1.5875,
      "step": 35
    },
    {
      "epoch": 0.9434889434889435,
      "grad_norm": 0.4300181269645691,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 1.6122,
      "step": 36
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.4537125825881958,
      "learning_rate": 7.192044826145771e-07,
      "loss": 1.6159,
      "step": 37
    },
    {
      "epoch": 0.9959049959049959,
      "grad_norm": 0.44113290309906006,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 1.6142,
      "step": 38
    },
    {
      "epoch": 1.0221130221130221,
      "grad_norm": 1.147554636001587,
      "learning_rate": 0.0,
      "loss": 2.9159,
      "step": 39
    }
  ],
  "logging_steps": 1,
  "max_steps": 39,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2251367690416947e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}