{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9335978527249388,
  "eval_steps": 250,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2333994631812347,
      "grad_norm": 8.384697914123535,
      "learning_rate": 8.959847237666421e-05,
      "loss": 0.3776,
      "step": 250
    },
    {
      "epoch": 0.2333994631812347,
      "eval_loss": 0.2075573056936264,
      "eval_runtime": 14.5853,
      "eval_samples_per_second": 5.965,
      "eval_steps_per_second": 5.965,
      "step": 250
    },
    {
      "epoch": 0.4667989263624694,
      "grad_norm": 4.4368462562561035,
      "learning_rate": 5.79860922155139e-05,
      "loss": 0.1658,
      "step": 500
    },
    {
      "epoch": 0.4667989263624694,
      "eval_loss": 0.13072766363620758,
      "eval_runtime": 14.6293,
      "eval_samples_per_second": 5.947,
      "eval_steps_per_second": 5.947,
      "step": 500
    },
    {
      "epoch": 0.7001983895437041,
      "grad_norm": 3.9202706813812256,
      "learning_rate": 2.1923372839080146e-05,
      "loss": 0.117,
      "step": 750
    },
    {
      "epoch": 0.7001983895437041,
      "eval_loss": 0.11273370683193207,
      "eval_runtime": 14.6276,
      "eval_samples_per_second": 5.948,
      "eval_steps_per_second": 5.948,
      "step": 750
    },
    {
      "epoch": 0.9335978527249388,
      "grad_norm": 3.244108200073242,
      "learning_rate": 1.1824717285160991e-06,
      "loss": 0.0995,
      "step": 1000
    },
    {
      "epoch": 0.9335978527249388,
      "eval_loss": 0.10820993036031723,
      "eval_runtime": 14.6135,
      "eval_samples_per_second": 5.953,
      "eval_steps_per_second": 5.953,
      "step": 1000
    }
  ],
  "logging_steps": 250,
  "max_steps": 1071,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.693476425669427e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}