{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0989010989010989,
  "eval_steps": 500,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 0.8822625875473022,
      "learning_rate": 0.0,
      "loss": 2.9966,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.1069581508636475,
      "learning_rate": 4e-05,
      "loss": 2.9598,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 0.8758227229118347,
      "learning_rate": 8e-05,
      "loss": 2.5775,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.0401133298873901,
      "learning_rate": 0.00012,
      "loss": 2.6196,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.4041666984558105,
      "learning_rate": 0.00016,
      "loss": 3.1798,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 1.4210084676742554,
      "learning_rate": 0.0002,
      "loss": 2.0834,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.1845953464508057,
      "learning_rate": 0.00019955654101995565,
      "loss": 2.3524,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.3485188484191895,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.616,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.0533819198608398,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.2391,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.1041414737701416,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.0831,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.7204957604408264,
      "learning_rate": 0.00019778270509977829,
      "loss": 0.8896,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.7176511287689209,
      "learning_rate": 0.00019733924611973393,
      "loss": 0.8995,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.7679543495178223,
      "learning_rate": 0.0001968957871396896,
      "loss": 0.7737,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.8583915829658508,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.8345,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5992399454116821,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.7105,
      "step": 15
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6285147048069120.0,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}