{
  "best_metric": 0.11403203755617142,
  "best_model_checkpoint": "outputs_yi1/checkpoint-50",
  "epoch": 7.68,
  "eval_steps": 10,
  "global_step": 96,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8,
      "grad_norm": 4.531487941741943,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.3938,
      "step": 10
    },
    {
      "epoch": 0.8,
      "eval_loss": 0.36487284302711487,
      "eval_runtime": 519.8453,
      "eval_samples_per_second": 2.126,
      "eval_steps_per_second": 0.267,
      "step": 10
    },
    {
      "epoch": 1.6,
      "grad_norm": 3.705087423324585,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.3223,
      "step": 20
    },
    {
      "epoch": 1.6,
      "eval_loss": 0.23971693217754364,
      "eval_runtime": 519.6952,
      "eval_samples_per_second": 2.126,
      "eval_steps_per_second": 0.267,
      "step": 20
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.8304980397224426,
      "learning_rate": 2e-05,
      "loss": 0.2031,
      "step": 30
    },
    {
      "epoch": 2.4,
      "eval_loss": 0.1636640578508377,
      "eval_runtime": 519.8736,
      "eval_samples_per_second": 2.126,
      "eval_steps_per_second": 0.267,
      "step": 30
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.6668256521224976,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.1511,
      "step": 40
    },
    {
      "epoch": 3.2,
      "eval_loss": 0.12974244356155396,
      "eval_runtime": 519.775,
      "eval_samples_per_second": 2.126,
      "eval_steps_per_second": 0.267,
      "step": 40
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.582798957824707,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.1209,
      "step": 50
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.11403203755617142,
      "eval_runtime": 519.6617,
      "eval_samples_per_second": 2.126,
      "eval_steps_per_second": 0.267,
      "step": 50
    },
    {
      "epoch": 4.8,
      "grad_norm": 1.1705131530761719,
      "learning_rate": 4e-05,
      "loss": 0.0943,
      "step": 60
    },
    {
      "epoch": 4.8,
      "eval_loss": 0.10507387667894363,
      "eval_runtime": 519.6411,
      "eval_samples_per_second": 2.126,
      "eval_steps_per_second": 0.267,
      "step": 60
    },
    {
      "epoch": 5.6,
      "grad_norm": 0.6869505643844604,
      "learning_rate": 4.666666666666667e-05,
      "loss": 0.0678,
      "step": 70
    },
    {
      "epoch": 5.6,
      "eval_loss": 0.10110265016555786,
      "eval_runtime": 519.6691,
      "eval_samples_per_second": 2.126,
      "eval_steps_per_second": 0.267,
      "step": 70
    },
    {
      "epoch": 6.4,
      "grad_norm": 0.953393280506134,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.0567,
      "step": 80
    },
    {
      "epoch": 6.4,
      "eval_loss": 0.10960907489061356,
      "eval_runtime": 519.4869,
      "eval_samples_per_second": 2.127,
      "eval_steps_per_second": 0.268,
      "step": 80
    },
    {
      "epoch": 7.2,
      "grad_norm": 0.7124423384666443,
      "learning_rate": 6e-05,
      "loss": 0.0411,
      "step": 90
    },
    {
      "epoch": 7.2,
      "eval_loss": 0.1117771789431572,
      "eval_runtime": 519.4695,
      "eval_samples_per_second": 2.127,
      "eval_steps_per_second": 0.268,
      "step": 90
    }
  ],
  "logging_steps": 10,
  "max_steps": 96,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3440514093129728e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}