{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.18018018018018017,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009009009009009009,
      "eval_loss": 0.91037517786026,
      "eval_runtime": 35.0182,
      "eval_samples_per_second": 13.364,
      "eval_steps_per_second": 6.682,
      "step": 1
    },
    {
      "epoch": 0.0045045045045045045,
      "grad_norm": 0.8114346265792847,
      "learning_rate": 5e-05,
      "loss": 3.5218,
      "step": 5
    },
    {
      "epoch": 0.009009009009009009,
      "grad_norm": 0.894910454750061,
      "learning_rate": 0.0001,
      "loss": 3.4258,
      "step": 10
    },
    {
      "epoch": 0.013513513513513514,
      "grad_norm": 1.7237918376922607,
      "learning_rate": 9.98292246503335e-05,
      "loss": 3.5609,
      "step": 15
    },
    {
      "epoch": 0.018018018018018018,
      "grad_norm": 1.525421380996704,
      "learning_rate": 9.931806517013612e-05,
      "loss": 3.4364,
      "step": 20
    },
    {
      "epoch": 0.02252252252252252,
      "grad_norm": 2.1673266887664795,
      "learning_rate": 9.847001329696653e-05,
      "loss": 3.0213,
      "step": 25
    },
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 2.467672109603882,
      "learning_rate": 9.729086208503174e-05,
      "loss": 3.2581,
      "step": 30
    },
    {
      "epoch": 0.03153153153153153,
      "grad_norm": 1.993414044380188,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.8398,
      "step": 35
    },
    {
      "epoch": 0.036036036036036036,
      "grad_norm": 2.092423439025879,
      "learning_rate": 9.397368756032445e-05,
      "loss": 2.5646,
      "step": 40
    },
    {
      "epoch": 0.04054054054054054,
      "grad_norm": 2.6000351905822754,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.7034,
      "step": 45
    },
    {
      "epoch": 0.04504504504504504,
      "grad_norm": 3.2636234760284424,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.5391,
      "step": 50
    },
    {
      "epoch": 0.04504504504504504,
      "eval_loss": 0.671043872833252,
      "eval_runtime": 35.5873,
      "eval_samples_per_second": 13.151,
      "eval_steps_per_second": 6.575,
      "step": 50
    },
    {
      "epoch": 0.04954954954954955,
      "grad_norm": 2.2121753692626953,
      "learning_rate": 8.678619553365659e-05,
      "loss": 3.0284,
      "step": 55
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 1.6796329021453857,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.949,
      "step": 60
    },
    {
      "epoch": 0.05855855855855856,
      "grad_norm": 1.8998647928237915,
      "learning_rate": 8.07106356344834e-05,
      "loss": 2.8002,
      "step": 65
    },
    {
      "epoch": 0.06306306306306306,
      "grad_norm": 1.9170352220535278,
      "learning_rate": 7.734740790612136e-05,
      "loss": 2.7579,
      "step": 70
    },
    {
      "epoch": 0.06756756756756757,
      "grad_norm": 2.008878707885742,
      "learning_rate": 7.379736965185368e-05,
      "loss": 2.893,
      "step": 75
    },
    {
      "epoch": 0.07207207207207207,
      "grad_norm": 2.4726173877716064,
      "learning_rate": 7.008477123264848e-05,
      "loss": 2.6539,
      "step": 80
    },
    {
      "epoch": 0.07657657657657657,
      "grad_norm": 2.354423761367798,
      "learning_rate": 6.623497346023418e-05,
      "loss": 2.4179,
      "step": 85
    },
    {
      "epoch": 0.08108108108108109,
      "grad_norm": 2.5047824382781982,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.6915,
      "step": 90
    },
    {
      "epoch": 0.08558558558558559,
      "grad_norm": 2.5813536643981934,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 2.5024,
      "step": 95
    },
    {
      "epoch": 0.09009009009009009,
      "grad_norm": 3.199880361557007,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.1346,
      "step": 100
    },
    {
      "epoch": 0.09009009009009009,
      "eval_loss": 0.630311906337738,
      "eval_runtime": 35.5839,
      "eval_samples_per_second": 13.152,
      "eval_steps_per_second": 6.576,
      "step": 100
    },
    {
      "epoch": 0.0945945945945946,
      "grad_norm": 2.01957368850708,
      "learning_rate": 5e-05,
      "loss": 2.8427,
      "step": 105
    },
    {
      "epoch": 0.0990990990990991,
      "grad_norm": 1.7157238721847534,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 2.6927,
      "step": 110
    },
    {
      "epoch": 0.1036036036036036,
      "grad_norm": 1.892593264579773,
      "learning_rate": 4.17702704859633e-05,
      "loss": 2.7364,
      "step": 115
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 1.8269039392471313,
      "learning_rate": 3.772572564296005e-05,
      "loss": 2.6854,
      "step": 120
    },
    {
      "epoch": 0.11261261261261261,
      "grad_norm": 2.3659868240356445,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 2.4613,
      "step": 125
    },
    {
      "epoch": 0.11711711711711711,
      "grad_norm": 2.2974438667297363,
      "learning_rate": 2.991522876735154e-05,
      "loss": 2.5113,
      "step": 130
    },
    {
      "epoch": 0.12162162162162163,
      "grad_norm": 2.6664466857910156,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 2.4434,
      "step": 135
    },
    {
      "epoch": 0.12612612612612611,
      "grad_norm": 2.160093069076538,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 2.4086,
      "step": 140
    },
    {
      "epoch": 0.13063063063063063,
      "grad_norm": 2.7726094722747803,
      "learning_rate": 1.928936436551661e-05,
      "loss": 2.5122,
      "step": 145
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 2.753997325897217,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 2.0832,
      "step": 150
    },
    {
      "epoch": 0.13513513513513514,
      "eval_loss": 0.6134156584739685,
      "eval_runtime": 35.6006,
      "eval_samples_per_second": 13.146,
      "eval_steps_per_second": 6.573,
      "step": 150
    },
    {
      "epoch": 0.13963963963963963,
      "grad_norm": 2.1443870067596436,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 2.7748,
      "step": 155
    },
    {
      "epoch": 0.14414414414414414,
      "grad_norm": 2.107656240463257,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 2.7739,
      "step": 160
    },
    {
      "epoch": 0.14864864864864866,
      "grad_norm": 1.9297782182693481,
      "learning_rate": 8.141676086873572e-06,
      "loss": 2.5551,
      "step": 165
    },
    {
      "epoch": 0.15315315315315314,
      "grad_norm": 2.201042890548706,
      "learning_rate": 6.026312439675552e-06,
      "loss": 2.6412,
      "step": 170
    },
    {
      "epoch": 0.15765765765765766,
      "grad_norm": 2.3642938137054443,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 2.6353,
      "step": 175
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 2.2860445976257324,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 2.6157,
      "step": 180
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 2.4721200466156006,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 2.4462,
      "step": 185
    },
    {
      "epoch": 0.17117117117117117,
      "grad_norm": 2.7481462955474854,
      "learning_rate": 6.819348298638839e-07,
      "loss": 2.5367,
      "step": 190
    },
    {
      "epoch": 0.17567567567567569,
      "grad_norm": 2.6995551586151123,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 2.5209,
      "step": 195
    },
    {
      "epoch": 0.18018018018018017,
      "grad_norm": 3.7238929271698,
      "learning_rate": 0.0,
      "loss": 2.0425,
      "step": 200
    },
    {
      "epoch": 0.18018018018018017,
      "eval_loss": 0.6100401282310486,
      "eval_runtime": 35.6094,
      "eval_samples_per_second": 13.143,
      "eval_steps_per_second": 6.571,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.51499696816128e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}