{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.37517241379310345,
  "eval_steps": 17,
  "global_step": 68,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005517241379310344,
      "eval_loss": 3.884207010269165,
      "eval_runtime": 4.4659,
      "eval_samples_per_second": 68.296,
      "eval_steps_per_second": 8.733,
      "step": 1
    },
    {
      "epoch": 0.016551724137931035,
      "grad_norm": 0.6788153648376465,
      "learning_rate": 3e-05,
      "loss": 3.8284,
      "step": 3
    },
    {
      "epoch": 0.03310344827586207,
      "grad_norm": 0.6769624352455139,
      "learning_rate": 6e-05,
      "loss": 3.7716,
      "step": 6
    },
    {
      "epoch": 0.0496551724137931,
      "grad_norm": 0.8537060618400574,
      "learning_rate": 9e-05,
      "loss": 3.8822,
      "step": 9
    },
    {
      "epoch": 0.06620689655172414,
      "grad_norm": 0.9294676780700684,
      "learning_rate": 9.997266286704631e-05,
      "loss": 3.7923,
      "step": 12
    },
    {
      "epoch": 0.08275862068965517,
      "grad_norm": 0.9163342118263245,
      "learning_rate": 9.98292246503335e-05,
      "loss": 3.315,
      "step": 15
    },
    {
      "epoch": 0.09379310344827586,
      "eval_loss": 3.4180614948272705,
      "eval_runtime": 4.4396,
      "eval_samples_per_second": 68.701,
      "eval_steps_per_second": 8.785,
      "step": 17
    },
    {
      "epoch": 0.0993103448275862,
      "grad_norm": 1.1075429916381836,
      "learning_rate": 9.956320346634876e-05,
      "loss": 3.3909,
      "step": 18
    },
    {
      "epoch": 0.11586206896551725,
      "grad_norm": 1.0358085632324219,
      "learning_rate": 9.917525374361912e-05,
      "loss": 3.0781,
      "step": 21
    },
    {
      "epoch": 0.13241379310344828,
      "grad_norm": 0.6941744685173035,
      "learning_rate": 9.86663298624003e-05,
      "loss": 3.1513,
      "step": 24
    },
    {
      "epoch": 0.1489655172413793,
      "grad_norm": 0.7888012528419495,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.815,
      "step": 27
    },
    {
      "epoch": 0.16551724137931034,
      "grad_norm": 0.6974669694900513,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.7661,
      "step": 30
    },
    {
      "epoch": 0.1820689655172414,
      "grad_norm": 0.7885407209396362,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.8794,
      "step": 33
    },
    {
      "epoch": 0.18758620689655173,
      "eval_loss": 2.820341110229492,
      "eval_runtime": 4.4584,
      "eval_samples_per_second": 68.411,
      "eval_steps_per_second": 8.748,
      "step": 34
    },
    {
      "epoch": 0.1986206896551724,
      "grad_norm": 0.8363791108131409,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.712,
      "step": 36
    },
    {
      "epoch": 0.21517241379310345,
      "grad_norm": 0.7954784035682678,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.5269,
      "step": 39
    },
    {
      "epoch": 0.2317241379310345,
      "grad_norm": 0.5852518081665039,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.4872,
      "step": 42
    },
    {
      "epoch": 0.2482758620689655,
      "grad_norm": 0.5917105674743652,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.6372,
      "step": 45
    },
    {
      "epoch": 0.26482758620689656,
      "grad_norm": 0.5113472938537598,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.3365,
      "step": 48
    },
    {
      "epoch": 0.2813793103448276,
      "grad_norm": 0.6705360412597656,
      "learning_rate": 8.894386393810563e-05,
      "loss": 2.512,
      "step": 51
    },
    {
      "epoch": 0.2813793103448276,
      "eval_loss": 2.4239444732666016,
      "eval_runtime": 4.4605,
      "eval_samples_per_second": 68.378,
      "eval_steps_per_second": 8.743,
      "step": 51
    },
    {
      "epoch": 0.2979310344827586,
      "grad_norm": 0.46963927149772644,
      "learning_rate": 8.73410738492077e-05,
      "loss": 2.3514,
      "step": 54
    },
    {
      "epoch": 0.31448275862068964,
      "grad_norm": 0.43661412596702576,
      "learning_rate": 8.564642241456986e-05,
      "loss": 2.3,
      "step": 57
    },
    {
      "epoch": 0.3310344827586207,
      "grad_norm": 0.48196548223495483,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.2038,
      "step": 60
    },
    {
      "epoch": 0.34758620689655173,
      "grad_norm": 0.47665441036224365,
      "learning_rate": 8.199842702516583e-05,
      "loss": 2.2897,
      "step": 63
    },
    {
      "epoch": 0.3641379310344828,
      "grad_norm": 0.4325224459171295,
      "learning_rate": 8.005405736415126e-05,
      "loss": 2.1655,
      "step": 66
    },
    {
      "epoch": 0.37517241379310345,
      "eval_loss": 2.257903575897217,
      "eval_runtime": 4.4787,
      "eval_samples_per_second": 68.1,
      "eval_steps_per_second": 8.708,
      "step": 68
    }
  ],
  "logging_steps": 3,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 17,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4322559189319680.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}