{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.6721311475409837,
  "eval_steps": 500,
  "global_step": 28,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.26229508196721313,
      "grad_norm": 0.9730982184410095,
      "learning_rate": 0.00018571428571428572,
      "loss": 9.4352,
      "step": 2
    },
    {
      "epoch": 0.5245901639344263,
      "grad_norm": 1.8006277084350586,
      "learning_rate": 0.00017142857142857143,
      "loss": 9.1689,
      "step": 4
    },
    {
      "epoch": 0.7868852459016393,
      "grad_norm": 1.831032395362854,
      "learning_rate": 0.00015714285714285716,
      "loss": 8.7485,
      "step": 6
    },
    {
      "epoch": 1.0491803278688525,
      "grad_norm": 2.2559938430786133,
      "learning_rate": 0.00014285714285714287,
      "loss": 8.3076,
      "step": 8
    },
    {
      "epoch": 1.3114754098360657,
      "grad_norm": 2.454803943634033,
      "learning_rate": 0.00012857142857142858,
      "loss": 7.8092,
      "step": 10
    },
    {
      "epoch": 1.5737704918032787,
      "grad_norm": 2.537230968475342,
      "learning_rate": 0.00011428571428571428,
      "loss": 7.8537,
      "step": 12
    },
    {
      "epoch": 1.8360655737704918,
      "grad_norm": 2.46220326423645,
      "learning_rate": 0.0001,
      "loss": 7.5995,
      "step": 14
    },
    {
      "epoch": 2.098360655737705,
      "grad_norm": 1.449030876159668,
      "learning_rate": 8.571428571428571e-05,
      "loss": 7.0811,
      "step": 16
    },
    {
      "epoch": 2.360655737704918,
      "grad_norm": 1.5821515321731567,
      "learning_rate": 7.142857142857143e-05,
      "loss": 7.2538,
      "step": 18
    },
    {
      "epoch": 2.6229508196721314,
      "grad_norm": 1.8766202926635742,
      "learning_rate": 5.714285714285714e-05,
      "loss": 7.068,
      "step": 20
    },
    {
      "epoch": 2.8852459016393444,
      "grad_norm": 1.4384005069732666,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 7.0955,
      "step": 22
    },
    {
      "epoch": 3.1475409836065573,
      "grad_norm": 1.8369501829147339,
      "learning_rate": 2.857142857142857e-05,
      "loss": 6.7993,
      "step": 24
    },
    {
      "epoch": 3.4098360655737707,
      "grad_norm": 1.4276976585388184,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 7.053,
      "step": 26
    },
    {
      "epoch": 3.6721311475409837,
      "grad_norm": 1.627907156944275,
      "learning_rate": 0.0,
      "loss": 7.1552,
      "step": 28
    },
    {
      "epoch": 3.6721311475409837,
      "step": 28,
      "total_flos": 131381250733656.0,
      "train_loss": 7.744901963642666,
      "train_runtime": 121.5966,
      "train_samples_per_second": 4.013,
      "train_steps_per_second": 0.23
    }
  ],
  "logging_steps": 2,
  "max_steps": 28,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 131381250733656.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}