{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.909090909090909,
  "eval_steps": 2,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.0655059739947319,
      "learning_rate": 1e-05,
      "loss": 10.3814,
      "step": 1
    },
    {
      "epoch": 0.18181818181818182,
      "eval_loss": 10.373859405517578,
      "eval_runtime": 0.0149,
      "eval_samples_per_second": 1210.594,
      "eval_steps_per_second": 67.255,
      "step": 1
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.06763208657503128,
      "learning_rate": 2e-05,
      "loss": 10.3794,
      "step": 2
    },
    {
      "epoch": 0.36363636363636365,
      "eval_loss": 10.37384033203125,
      "eval_runtime": 0.014,
      "eval_samples_per_second": 1286.509,
      "eval_steps_per_second": 71.473,
      "step": 2
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.05924370139837265,
      "learning_rate": 3e-05,
      "loss": 10.3799,
      "step": 3
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.07271450757980347,
      "learning_rate": 4e-05,
      "loss": 10.3762,
      "step": 4
    },
    {
      "epoch": 0.7272727272727273,
      "eval_loss": 10.373745918273926,
      "eval_runtime": 0.0137,
      "eval_samples_per_second": 1310.47,
      "eval_steps_per_second": 72.804,
      "step": 4
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.07363289594650269,
      "learning_rate": 5e-05,
      "loss": 10.3796,
      "step": 5
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.09829460829496384,
      "learning_rate": 6e-05,
      "loss": 15.5502,
      "step": 6
    },
    {
      "epoch": 1.0909090909090908,
      "eval_loss": 10.373668670654297,
      "eval_runtime": 0.0138,
      "eval_samples_per_second": 1302.219,
      "eval_steps_per_second": 72.346,
      "step": 6
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.0690544992685318,
      "learning_rate": 7e-05,
      "loss": 10.4244,
      "step": 7
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.0672140046954155,
      "learning_rate": 8e-05,
      "loss": 10.3356,
      "step": 8
    },
    {
      "epoch": 1.4545454545454546,
      "eval_loss": 10.373486518859863,
      "eval_runtime": 0.0138,
      "eval_samples_per_second": 1308.993,
      "eval_steps_per_second": 72.722,
      "step": 8
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.06882895529270172,
      "learning_rate": 9e-05,
      "loss": 10.3282,
      "step": 9
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.07141602784395218,
      "learning_rate": 0.0001,
      "loss": 10.411,
      "step": 10
    },
    {
      "epoch": 1.8181818181818183,
      "eval_loss": 10.373241424560547,
      "eval_runtime": 0.0139,
      "eval_samples_per_second": 1298.613,
      "eval_steps_per_second": 72.145,
      "step": 10
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.10249509662389755,
      "learning_rate": 9.330127018922194e-05,
      "loss": 15.5975,
      "step": 11
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 0.07137065380811691,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3779,
      "step": 12
    },
    {
      "epoch": 2.1818181818181817,
      "eval_loss": 10.373038291931152,
      "eval_runtime": 0.0138,
      "eval_samples_per_second": 1305.236,
      "eval_steps_per_second": 72.513,
      "step": 12
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 0.06905053555965424,
      "learning_rate": 5e-05,
      "loss": 10.3807,
      "step": 13
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 0.0683932676911354,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3721,
      "step": 14
    },
    {
      "epoch": 2.5454545454545454,
      "eval_loss": 10.372879028320312,
      "eval_runtime": 0.0138,
      "eval_samples_per_second": 1305.011,
      "eval_steps_per_second": 72.501,
      "step": 14
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.07640717178583145,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.3795,
      "step": 15
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.06950083374977112,
      "learning_rate": 0.0,
      "loss": 10.3801,
      "step": 16
    },
    {
      "epoch": 2.909090909090909,
      "eval_loss": 10.372831344604492,
      "eval_runtime": 0.0137,
      "eval_samples_per_second": 1318.549,
      "eval_steps_per_second": 73.253,
      "step": 16
    }
  ],
  "logging_steps": 1,
  "max_steps": 16,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3347356581888.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}