{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 4527,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3313452617627568,
      "grad_norm": 4.3162078857421875,
      "learning_rate": 4.448862381267948e-05,
      "loss": 0.5905,
      "step": 500
    },
    {
      "epoch": 0.6626905235255136,
      "grad_norm": 3.045156717300415,
      "learning_rate": 3.89662027833002e-05,
      "loss": 0.526,
      "step": 1000
    },
    {
      "epoch": 0.9940357852882704,
      "grad_norm": 1.9955639839172363,
      "learning_rate": 3.344378175392092e-05,
      "loss": 0.5096,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.4867047369480133,
      "eval_runtime": 22.7867,
      "eval_samples_per_second": 66.223,
      "eval_steps_per_second": 8.294,
      "step": 1509
    },
    {
      "epoch": 1.3253810470510272,
      "grad_norm": 5.011231422424316,
      "learning_rate": 2.792136072454164e-05,
      "loss": 0.4614,
      "step": 2000
    },
    {
      "epoch": 1.6567263088137838,
      "grad_norm": 3.223392963409424,
      "learning_rate": 2.239893969516236e-05,
      "loss": 0.4484,
      "step": 2500
    },
    {
      "epoch": 1.9880715705765408,
      "grad_norm": 6.150548934936523,
      "learning_rate": 1.687651866578308e-05,
      "loss": 0.4356,
      "step": 3000
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.4857780337333679,
      "eval_runtime": 22.7944,
      "eval_samples_per_second": 66.2,
      "eval_steps_per_second": 8.291,
      "step": 3018
    },
    {
      "epoch": 2.3194168323392974,
      "grad_norm": 3.034126043319702,
      "learning_rate": 1.13540976364038e-05,
      "loss": 0.3865,
      "step": 3500
    },
    {
      "epoch": 2.6507620941020544,
      "grad_norm": 2.4947311878204346,
      "learning_rate": 5.83167660702452e-06,
      "loss": 0.3881,
      "step": 4000
    },
    {
      "epoch": 2.982107355864811,
      "grad_norm": 2.1063663959503174,
      "learning_rate": 3.092555776452397e-07,
      "loss": 0.3846,
      "step": 4500
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5579625368118286,
      "eval_runtime": 22.7791,
      "eval_samples_per_second": 66.245,
      "eval_steps_per_second": 8.297,
      "step": 4527
    }
  ],
  "logging_steps": 500,
  "max_steps": 4527,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 4796704972652544.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}