{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03163055511624229,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006326111023248458,
      "eval_loss": 0.9079214334487915,
      "eval_runtime": 81.9882,
      "eval_samples_per_second": 8.123,
      "eval_steps_per_second": 4.062,
      "step": 1
    },
    {
      "epoch": 0.003163055511624229,
      "grad_norm": 0.2053448110818863,
      "learning_rate": 5e-05,
      "loss": 0.8975,
      "step": 5
    },
    {
      "epoch": 0.006326111023248458,
      "grad_norm": 0.21027112007141113,
      "learning_rate": 0.0001,
      "loss": 0.8808,
      "step": 10
    },
    {
      "epoch": 0.006326111023248458,
      "eval_loss": 0.823966383934021,
      "eval_runtime": 82.0336,
      "eval_samples_per_second": 8.119,
      "eval_steps_per_second": 4.059,
      "step": 10
    },
    {
      "epoch": 0.009489166534872686,
      "grad_norm": 0.2593160569667816,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.7957,
      "step": 15
    },
    {
      "epoch": 0.012652222046496917,
      "grad_norm": 0.29066306352615356,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.7148,
      "step": 20
    },
    {
      "epoch": 0.012652222046496917,
      "eval_loss": 0.6664239764213562,
      "eval_runtime": 82.0682,
      "eval_samples_per_second": 8.115,
      "eval_steps_per_second": 4.058,
      "step": 20
    },
    {
      "epoch": 0.015815277558121146,
      "grad_norm": 0.26904571056365967,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.6598,
      "step": 25
    },
    {
      "epoch": 0.018978333069745373,
      "grad_norm": 0.31456199288368225,
      "learning_rate": 5e-05,
      "loss": 0.613,
      "step": 30
    },
    {
      "epoch": 0.018978333069745373,
      "eval_loss": 0.5932477116584778,
      "eval_runtime": 82.3696,
      "eval_samples_per_second": 8.086,
      "eval_steps_per_second": 4.043,
      "step": 30
    },
    {
      "epoch": 0.022141388581369603,
      "grad_norm": 0.34897688031196594,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.5741,
      "step": 35
    },
    {
      "epoch": 0.025304444092993834,
      "grad_norm": 0.34637877345085144,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.5633,
      "step": 40
    },
    {
      "epoch": 0.025304444092993834,
      "eval_loss": 0.56394362449646,
      "eval_runtime": 82.3016,
      "eval_samples_per_second": 8.092,
      "eval_steps_per_second": 4.046,
      "step": 40
    },
    {
      "epoch": 0.02846749960461806,
      "grad_norm": 0.37049219012260437,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.5798,
      "step": 45
    },
    {
      "epoch": 0.03163055511624229,
      "grad_norm": 0.3430643081665039,
      "learning_rate": 0.0,
      "loss": 0.5545,
      "step": 50
    },
    {
      "epoch": 0.03163055511624229,
      "eval_loss": 0.5589888095855713,
      "eval_runtime": 82.3564,
      "eval_samples_per_second": 8.087,
      "eval_steps_per_second": 4.043,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.74263604609024e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}