{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 30,
  "global_step": 113,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08849557522123894,
      "grad_norm": 0.5378276109695435,
      "learning_rate": 9.808007740920646e-05,
      "loss": 0.4426,
      "step": 10
    },
    {
      "epoch": 0.17699115044247787,
      "grad_norm": 0.08370009064674377,
      "learning_rate": 9.246775374701139e-05,
      "loss": 0.0061,
      "step": 20
    },
    {
      "epoch": 0.26548672566371684,
      "grad_norm": 0.010601534508168697,
      "learning_rate": 8.359403809285053e-05,
      "loss": 0.004,
      "step": 30
    },
    {
      "epoch": 0.26548672566371684,
      "eval_loss": 0.0038232754450291395,
      "eval_runtime": 56.0996,
      "eval_samples_per_second": 8.913,
      "eval_steps_per_second": 0.232,
      "step": 30
    },
    {
      "epoch": 0.35398230088495575,
      "grad_norm": 0.03688598424196243,
      "learning_rate": 7.214040433267198e-05,
      "loss": 0.0038,
      "step": 40
    },
    {
      "epoch": 0.4424778761061947,
      "grad_norm": 0.013299869373440742,
      "learning_rate": 5.8986456074589404e-05,
      "loss": 0.0038,
      "step": 50
    },
    {
      "epoch": 0.5309734513274337,
      "grad_norm": 0.08473875373601913,
      "learning_rate": 4.5142375815355706e-05,
      "loss": 0.0037,
      "step": 60
    },
    {
      "epoch": 0.5309734513274337,
      "eval_loss": 0.0035941482055932283,
      "eval_runtime": 56.1024,
      "eval_samples_per_second": 8.912,
      "eval_steps_per_second": 0.232,
      "step": 60
    },
    {
      "epoch": 0.6194690265486725,
      "grad_norm": 0.008843529969453812,
      "learning_rate": 3.167134605250938e-05,
      "loss": 0.0037,
      "step": 70
    },
    {
      "epoch": 0.7079646017699115,
      "grad_norm": 0.006533902138471603,
      "learning_rate": 1.960790016056801e-05,
      "loss": 0.0036,
      "step": 80
    },
    {
      "epoch": 0.7964601769911505,
      "grad_norm": 0.06442264467477798,
      "learning_rate": 9.878473431161767e-06,
      "loss": 0.0035,
      "step": 90
    },
    {
      "epoch": 0.7964601769911505,
      "eval_loss": 0.003458332037553191,
      "eval_runtime": 56.0617,
      "eval_samples_per_second": 8.919,
      "eval_steps_per_second": 0.232,
      "step": 90
    },
    {
      "epoch": 0.8849557522123894,
      "grad_norm": 0.06732333451509476,
      "learning_rate": 3.230255711220992e-06,
      "loss": 0.0034,
      "step": 100
    },
    {
      "epoch": 0.9734513274336283,
      "grad_norm": 0.01167540717869997,
      "learning_rate": 1.7380953630678488e-07,
      "loss": 0.0035,
      "step": 110
    },
    {
      "epoch": 1.0,
      "step": 113,
      "total_flos": 4.179655240942879e+17,
      "train_loss": 0.042722021724072703,
      "train_runtime": 1759.0892,
      "train_samples_per_second": 2.558,
      "train_steps_per_second": 0.064
    }
  ],
  "logging_steps": 10,
  "max_steps": 113,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 4.179655240942879e+17,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}