{
  "best_metric": 0.22581644356250763,
  "best_model_checkpoint": "./beans_outputs/checkpoint-119",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 119,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 1.3762181997299194,
      "learning_rate": 1.831932773109244e-05,
      "loss": 0.9859,
      "step": 10
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9323308270676691,
      "eval_loss": 0.7491655945777893,
      "eval_runtime": 5.5873,
      "eval_samples_per_second": 23.804,
      "eval_steps_per_second": 0.537,
      "step": 17
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 1.1865174770355225,
      "learning_rate": 1.6638655462184877e-05,
      "loss": 0.8079,
      "step": 20
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 1.1438422203063965,
      "learning_rate": 1.4957983193277313e-05,
      "loss": 0.6763,
      "step": 30
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9624060150375939,
      "eval_loss": 0.527583658695221,
      "eval_runtime": 5.462,
      "eval_samples_per_second": 24.35,
      "eval_steps_per_second": 0.549,
      "step": 34
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 1.21797513961792,
      "learning_rate": 1.3277310924369749e-05,
      "loss": 0.5492,
      "step": 40
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 1.011806607246399,
      "learning_rate": 1.1596638655462186e-05,
      "loss": 0.4605,
      "step": 50
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9624060150375939,
      "eval_loss": 0.37262409925460815,
      "eval_runtime": 5.3091,
      "eval_samples_per_second": 25.051,
      "eval_steps_per_second": 0.565,
      "step": 51
    },
    {
      "epoch": 3.5294117647058822,
      "grad_norm": 1.1743957996368408,
      "learning_rate": 9.915966386554622e-06,
      "loss": 0.404,
      "step": 60
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9699248120300752,
      "eval_loss": 0.29651108384132385,
      "eval_runtime": 5.5743,
      "eval_samples_per_second": 23.86,
      "eval_steps_per_second": 0.538,
      "step": 68
    },
    {
      "epoch": 4.117647058823529,
      "grad_norm": 1.0325419902801514,
      "learning_rate": 8.23529411764706e-06,
      "loss": 0.3266,
      "step": 70
    },
    {
      "epoch": 4.705882352941177,
      "grad_norm": 1.3537858724594116,
      "learning_rate": 6.5546218487394966e-06,
      "loss": 0.3169,
      "step": 80
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9699248120300752,
      "eval_loss": 0.2537935972213745,
      "eval_runtime": 5.43,
      "eval_samples_per_second": 24.493,
      "eval_steps_per_second": 0.552,
      "step": 85
    },
    {
      "epoch": 5.294117647058823,
      "grad_norm": 0.9739072918891907,
      "learning_rate": 4.873949579831933e-06,
      "loss": 0.2762,
      "step": 90
    },
    {
      "epoch": 5.882352941176471,
      "grad_norm": 0.8430888056755066,
      "learning_rate": 3.1932773109243696e-06,
      "loss": 0.2536,
      "step": 100
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9774436090225563,
      "eval_loss": 0.22734107077121735,
      "eval_runtime": 5.2306,
      "eval_samples_per_second": 25.427,
      "eval_steps_per_second": 0.574,
      "step": 102
    },
    {
      "epoch": 6.470588235294118,
      "grad_norm": 1.0927995443344116,
      "learning_rate": 1.5126050420168068e-06,
      "loss": 0.2633,
      "step": 110
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9699248120300752,
      "eval_loss": 0.22581644356250763,
      "eval_runtime": 5.4121,
      "eval_samples_per_second": 24.575,
      "eval_steps_per_second": 0.554,
      "step": 119
    },
    {
      "epoch": 7.0,
      "step": 119,
      "total_flos": 5.608920478833746e+17,
      "train_loss": 0.46638633623844433,
      "train_runtime": 404.4816,
      "train_samples_per_second": 17.895,
      "train_steps_per_second": 0.294
    }
  ],
  "logging_steps": 10,
  "max_steps": 119,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 5.608920478833746e+17,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}