{
  "best_global_step": 30,
  "best_metric": 0.4217299818992615,
  "best_model_checkpoint": "/tmp/checkpoints_/job_0d4521ef-134d-4da5-986e-64cc35a0beaa/checkpoint-30",
  "epoch": 0.6666666666666666,
  "eval_steps": 10,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022222222222222223,
      "grad_norm": 10.740789413452148,
      "learning_rate": 0.0,
      "loss": 4.085967063903809,
      "step": 1
    },
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 9.23949909210205,
      "learning_rate": 1e-05,
      "loss": 3.999408006668091,
      "step": 2
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 12.284346580505371,
      "learning_rate": 2e-05,
      "loss": 4.025123596191406,
      "step": 3
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 9.18883991241455,
      "learning_rate": 3e-05,
      "loss": 3.792623519897461,
      "step": 4
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 7.945703983306885,
      "learning_rate": 4e-05,
      "loss": 3.6587512493133545,
      "step": 5
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 7.3979291915893555,
      "learning_rate": 5e-05,
      "loss": 3.2053868770599365,
      "step": 6
    },
    {
      "epoch": 0.15555555555555556,
      "grad_norm": 6.683148384094238,
      "learning_rate": 4.999270035200483e-05,
      "loss": 3.075692653656006,
      "step": 7
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 5.784440994262695,
      "learning_rate": 4.997080567080817e-05,
      "loss": 2.732858419418335,
      "step": 8
    },
    {
      "epoch": 0.2,
      "grad_norm": 5.552517414093018,
      "learning_rate": 4.9934328742287285e-05,
      "loss": 2.6176648139953613,
      "step": 9
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 6.0725884437561035,
      "learning_rate": 4.988329086794122e-05,
      "loss": 2.3721094131469727,
      "step": 10
    },
    {
      "epoch": 0.2222222222222222,
      "eval_loss": 2.18822979927063,
      "eval_runtime": 0.6219,
      "eval_samples_per_second": 32.162,
      "eval_steps_per_second": 8.04,
      "step": 10
    },
    {
      "epoch": 0.24444444444444444,
      "grad_norm": 5.783756732940674,
      "learning_rate": 4.981772185245135e-05,
      "loss": 2.302637815475464,
      "step": 11
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 5.778560638427734,
      "learning_rate": 4.973765998627628e-05,
      "loss": 2.1610288619995117,
      "step": 12
    },
    {
      "epoch": 0.28888888888888886,
      "grad_norm": 5.138077735900879,
      "learning_rate": 4.964315202329127e-05,
      "loss": 1.8655757904052734,
      "step": 13
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 5.479531764984131,
      "learning_rate": 4.953425315348534e-05,
      "loss": 1.749828815460205,
      "step": 14
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 5.30877161026001,
      "learning_rate": 4.9411026970731805e-05,
      "loss": 1.5302460193634033,
      "step": 15
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 5.6600260734558105,
      "learning_rate": 4.92735454356513e-05,
      "loss": 1.394092082977295,
      "step": 16
    },
    {
      "epoch": 0.37777777777777777,
      "grad_norm": 4.990982532501221,
      "learning_rate": 4.9121888833588795e-05,
      "loss": 1.2497376203536987,
      "step": 17
    },
    {
      "epoch": 0.4,
      "grad_norm": 5.325894832611084,
      "learning_rate": 4.8956145727729156e-05,
      "loss": 1.2083749771118164,
      "step": 18
    },
    {
      "epoch": 0.4222222222222222,
      "grad_norm": 5.7776618003845215,
      "learning_rate": 4.877641290737884e-05,
      "loss": 1.1976934671401978,
      "step": 19
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 5.4699249267578125,
      "learning_rate": 4.858279533144358e-05,
      "loss": 0.9608996510505676,
      "step": 20
    },
    {
      "epoch": 0.4444444444444444,
      "eval_loss": 0.9114124178886414,
      "eval_runtime": 0.6193,
      "eval_samples_per_second": 32.293,
      "eval_steps_per_second": 8.073,
      "step": 20
    },
    {
      "epoch": 0.4666666666666667,
      "grad_norm": 4.757471561431885,
      "learning_rate": 4.837540606713538e-05,
      "loss": 0.9015084505081177,
      "step": 21
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 4.183780193328857,
      "learning_rate": 4.815436622394441e-05,
      "loss": 0.7763562202453613,
      "step": 22
    },
    {
      "epoch": 0.5111111111111111,
      "grad_norm": 6.7120466232299805,
      "learning_rate": 4.791980488291456e-05,
      "loss": 0.9629366993904114,
      "step": 23
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 3.9772117137908936,
      "learning_rate": 4.767185902126364e-05,
      "loss": 0.7046512365341187,
      "step": 24
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 4.194173336029053,
      "learning_rate": 4.7410673432392596e-05,
      "loss": 0.6537044048309326,
      "step": 25
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 4.1374287605285645,
      "learning_rate": 4.713640064133025e-05,
      "loss": 0.5453305244445801,
      "step": 26
    },
    {
      "epoch": 0.6,
      "grad_norm": 4.520692825317383,
      "learning_rate": 4.684920081566295e-05,
      "loss": 0.6430343985557556,
      "step": 27
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 6.000478267669678,
      "learning_rate": 4.654924167200123e-05,
      "loss": 0.655798614025116,
      "step": 28
    },
    {
      "epoch": 0.6444444444444445,
      "grad_norm": 3.8246989250183105,
      "learning_rate": 4.6236698378038026e-05,
      "loss": 0.5909295082092285,
      "step": 29
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 3.1917481422424316,
      "learning_rate": 4.5911753450255665e-05,
      "loss": 0.3079158067703247,
      "step": 30
    },
    {
      "epoch": 0.6666666666666666,
      "eval_loss": 0.4217299818992615,
      "eval_runtime": 0.6115,
      "eval_samples_per_second": 32.706,
      "eval_steps_per_second": 8.176,
      "step": 30
    }
  ],
  "logging_steps": 1,
  "max_steps": 135,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 32866257768960.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}