{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08620689655172414,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008620689655172414,
      "eval_loss": 1.9068092107772827,
      "eval_runtime": 17.6833,
      "eval_samples_per_second": 11.027,
      "eval_steps_per_second": 1.414,
      "step": 1
    },
    {
      "epoch": 0.02586206896551724,
      "grad_norm": 42.144020080566406,
      "learning_rate": 3e-05,
      "loss": 7.5638,
      "step": 3
    },
    {
      "epoch": 0.04310344827586207,
      "eval_loss": 1.08273184299469,
      "eval_runtime": 17.8695,
      "eval_samples_per_second": 10.912,
      "eval_steps_per_second": 1.399,
      "step": 5
    },
    {
      "epoch": 0.05172413793103448,
      "grad_norm": 23.90378761291504,
      "learning_rate": 6e-05,
      "loss": 5.3623,
      "step": 6
    },
    {
      "epoch": 0.07758620689655173,
      "grad_norm": 28.774568557739258,
      "learning_rate": 9e-05,
      "loss": 4.0848,
      "step": 9
    },
    {
      "epoch": 0.08620689655172414,
      "eval_loss": 0.7605625987052917,
      "eval_runtime": 17.9379,
      "eval_samples_per_second": 10.871,
      "eval_steps_per_second": 1.394,
      "step": 10
    }
  ],
  "logging_steps": 3,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.430998008987648e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}