{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6015037593984962,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0030075187969924814,
      "eval_loss": 10.820727348327637,
      "eval_runtime": 0.858,
      "eval_samples_per_second": 163.161,
      "eval_steps_per_second": 81.58,
      "step": 1
    },
    {
      "epoch": 0.03007518796992481,
      "grad_norm": 0.24175788462162018,
      "learning_rate": 0.0002,
      "loss": 10.8226,
      "step": 10
    },
    {
      "epoch": 0.06015037593984962,
      "grad_norm": 0.24899822473526,
      "learning_rate": 0.0002,
      "loss": 10.81,
      "step": 20
    },
    {
      "epoch": 0.09022556390977443,
      "grad_norm": 0.3050399124622345,
      "learning_rate": 0.0002,
      "loss": 10.7847,
      "step": 30
    },
    {
      "epoch": 0.12030075187969924,
      "grad_norm": 0.21318531036376953,
      "learning_rate": 0.0002,
      "loss": 10.7543,
      "step": 40
    },
    {
      "epoch": 0.15037593984962405,
      "grad_norm": 0.15988190472126007,
      "learning_rate": 0.0002,
      "loss": 10.7285,
      "step": 50
    },
    {
      "epoch": 0.15037593984962405,
      "eval_loss": 10.709030151367188,
      "eval_runtime": 0.4624,
      "eval_samples_per_second": 302.784,
      "eval_steps_per_second": 151.392,
      "step": 50
    },
    {
      "epoch": 0.18045112781954886,
      "grad_norm": 0.12351339310407639,
      "learning_rate": 0.0002,
      "loss": 10.7157,
      "step": 60
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.10733628273010254,
      "learning_rate": 0.0002,
      "loss": 10.7116,
      "step": 70
    },
    {
      "epoch": 0.24060150375939848,
      "grad_norm": 0.09820961952209473,
      "learning_rate": 0.0002,
      "loss": 10.7077,
      "step": 80
    },
    {
      "epoch": 0.2706766917293233,
      "grad_norm": 0.08355368673801422,
      "learning_rate": 0.0002,
      "loss": 10.7058,
      "step": 90
    },
    {
      "epoch": 0.3007518796992481,
      "grad_norm": 0.08498694747686386,
      "learning_rate": 0.0002,
      "loss": 10.7083,
      "step": 100
    },
    {
      "epoch": 0.3007518796992481,
      "eval_loss": 10.692218780517578,
      "eval_runtime": 0.4623,
      "eval_samples_per_second": 302.811,
      "eval_steps_per_second": 151.406,
      "step": 100
    },
    {
      "epoch": 0.3308270676691729,
      "grad_norm": 0.10568591207265854,
      "learning_rate": 0.0002,
      "loss": 10.703,
      "step": 110
    },
    {
      "epoch": 0.3609022556390977,
      "grad_norm": 0.10359843820333481,
      "learning_rate": 0.0002,
      "loss": 10.6997,
      "step": 120
    },
    {
      "epoch": 0.39097744360902253,
      "grad_norm": 0.09477504342794418,
      "learning_rate": 0.0002,
      "loss": 10.7039,
      "step": 130
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.10229877382516861,
      "learning_rate": 0.0002,
      "loss": 10.694,
      "step": 140
    },
    {
      "epoch": 0.45112781954887216,
      "grad_norm": 0.13511568307876587,
      "learning_rate": 0.0002,
      "loss": 10.6899,
      "step": 150
    },
    {
      "epoch": 0.45112781954887216,
      "eval_loss": 10.677408218383789,
      "eval_runtime": 0.4665,
      "eval_samples_per_second": 300.117,
      "eval_steps_per_second": 150.058,
      "step": 150
    },
    {
      "epoch": 0.48120300751879697,
      "grad_norm": 0.10884358733892441,
      "learning_rate": 0.0002,
      "loss": 10.6897,
      "step": 160
    },
    {
      "epoch": 0.5112781954887218,
      "grad_norm": 0.08635402470827103,
      "learning_rate": 0.0002,
      "loss": 10.6819,
      "step": 170
    },
    {
      "epoch": 0.5413533834586466,
      "grad_norm": 0.11650286614894867,
      "learning_rate": 0.0002,
      "loss": 10.6761,
      "step": 180
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.08204352855682373,
      "learning_rate": 0.0002,
      "loss": 10.6727,
      "step": 190
    },
    {
      "epoch": 0.6015037593984962,
      "grad_norm": 0.10318433493375778,
      "learning_rate": 0.0002,
      "loss": 10.6705,
      "step": 200
    },
    {
      "epoch": 0.6015037593984962,
      "eval_loss": 10.65206527709961,
      "eval_runtime": 0.4867,
      "eval_samples_per_second": 287.665,
      "eval_steps_per_second": 143.833,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 32811830476800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}