{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8526419797444476,
  "eval_steps": 15000,
  "global_step": 165000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16842199815858616,
      "grad_norm": 26.715444564819336,
      "learning_rate": 2.524392297760063e-05,
      "loss": 2.7341,
      "step": 15000
    },
    {
      "epoch": 0.16842199815858616,
      "eval_loss": 2.285806894302368,
      "eval_runtime": 1158.8497,
      "eval_samples_per_second": 153.708,
      "eval_steps_per_second": 1.201,
      "step": 15000
    },
    {
      "epoch": 0.3368439963171723,
      "grad_norm": 19.40599250793457,
      "learning_rate": 2.7722551789958272e-05,
      "loss": 2.3026,
      "step": 30000
    },
    {
      "epoch": 0.3368439963171723,
      "eval_loss": 2.0999577045440674,
      "eval_runtime": 1151.5052,
      "eval_samples_per_second": 154.688,
      "eval_steps_per_second": 1.209,
      "step": 30000
    },
    {
      "epoch": 0.5052659944757585,
      "grad_norm": 22.466140747070312,
      "learning_rate": 2.4916256526376855e-05,
      "loss": 2.1131,
      "step": 45000
    },
    {
      "epoch": 0.5052659944757585,
      "eval_loss": 1.940854787826538,
      "eval_runtime": 1136.4523,
      "eval_samples_per_second": 156.737,
      "eval_steps_per_second": 1.225,
      "step": 45000
    },
    {
      "epoch": 0.6736879926343446,
      "grad_norm": 17.693044662475586,
      "learning_rate": 2.2110335535303257e-05,
      "loss": 1.9718,
      "step": 60000
    },
    {
      "epoch": 0.6736879926343446,
      "eval_loss": 1.83816397190094,
      "eval_runtime": 1139.1127,
      "eval_samples_per_second": 156.371,
      "eval_steps_per_second": 1.222,
      "step": 60000
    },
    {
      "epoch": 0.8421099907929308,
      "grad_norm": 17.317466735839844,
      "learning_rate": 1.930404027172184e-05,
      "loss": 1.8708,
      "step": 75000
    },
    {
      "epoch": 0.8421099907929308,
      "eval_loss": 1.7577824592590332,
      "eval_runtime": 1145.3619,
      "eval_samples_per_second": 155.518,
      "eval_steps_per_second": 1.215,
      "step": 75000
    },
    {
      "epoch": 1.010531988951517,
      "grad_norm": 23.801891326904297,
      "learning_rate": 1.6498306416902146e-05,
      "loss": 1.8018,
      "step": 90000
    },
    {
      "epoch": 1.010531988951517,
      "eval_loss": 1.6910173892974854,
      "eval_runtime": 1141.2463,
      "eval_samples_per_second": 156.078,
      "eval_steps_per_second": 1.22,
      "step": 90000
    },
    {
      "epoch": 1.1789539871101031,
      "grad_norm": 21.042640686035156,
      "learning_rate": 1.3692011153320733e-05,
      "loss": 1.7164,
      "step": 105000
    },
    {
      "epoch": 1.1789539871101031,
      "eval_loss": 1.631761908531189,
      "eval_runtime": 1145.0797,
      "eval_samples_per_second": 155.556,
      "eval_steps_per_second": 1.216,
      "step": 105000
    },
    {
      "epoch": 1.3473759852686893,
      "grad_norm": 27.30491828918457,
      "learning_rate": 1.0886090162247132e-05,
      "loss": 1.6587,
      "step": 120000
    },
    {
      "epoch": 1.3473759852686893,
      "eval_loss": 1.5805171728134155,
      "eval_runtime": 1146.9008,
      "eval_samples_per_second": 155.309,
      "eval_steps_per_second": 1.214,
      "step": 120000
    },
    {
      "epoch": 1.5157979834272752,
      "grad_norm": 9.642218589782715,
      "learning_rate": 8.079982034919624e-06,
      "loss": 1.6155,
      "step": 135000
    },
    {
      "epoch": 1.5157979834272752,
      "eval_loss": 1.5369038581848145,
      "eval_runtime": 1144.2178,
      "eval_samples_per_second": 155.673,
      "eval_steps_per_second": 1.217,
      "step": 135000
    },
    {
      "epoch": 1.6842199815858616,
      "grad_norm": 21.853740692138672,
      "learning_rate": 5.273873907592118e-06,
      "loss": 1.5718,
      "step": 150000
    },
    {
      "epoch": 1.6842199815858616,
      "eval_loss": 1.4996742010116577,
      "eval_runtime": 1144.5949,
      "eval_samples_per_second": 155.622,
      "eval_steps_per_second": 1.216,
      "step": 150000
    },
    {
      "epoch": 1.8526419797444476,
      "grad_norm": 20.76922607421875,
      "learning_rate": 2.4675786440107043e-06,
      "loss": 1.5311,
      "step": 165000
    },
    {
      "epoch": 1.8526419797444476,
      "eval_loss": 1.469059944152832,
      "eval_runtime": 1146.7492,
      "eval_samples_per_second": 155.33,
      "eval_steps_per_second": 1.214,
      "step": 165000
    }
  ],
  "logging_steps": 15000,
  "max_steps": 178124,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 15000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2303504218111662e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}