{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.6956521739130435,
  "eval_steps": 500,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 0.37405514921147065,
      "learning_rate": 5e-06,
      "loss": 3.6225,
      "step": 1
    },
    {
      "epoch": 0.6956521739130435,
      "eval_loss": 3.654219627380371,
      "eval_runtime": 0.517,
      "eval_samples_per_second": 34.814,
      "eval_steps_per_second": 9.671,
      "step": 2
    },
    {
      "epoch": 1.6956521739130435,
      "eval_loss": 3.6513125896453857,
      "eval_runtime": 0.5093,
      "eval_samples_per_second": 35.342,
      "eval_steps_per_second": 9.817,
      "step": 4
    },
    {
      "epoch": 2.3478260869565215,
      "grad_norm": 0.3847901447716293,
      "learning_rate": 4.774575140626317e-07,
      "loss": 5.3254,
      "step": 5
    },
    {
      "epoch": 2.6956521739130435,
      "eval_loss": 3.6504335403442383,
      "eval_runtime": 0.5036,
      "eval_samples_per_second": 35.74,
      "eval_steps_per_second": 9.928,
      "step": 6
    },
    {
      "epoch": 2.6956521739130435,
      "step": 6,
      "total_flos": 388288208699392.0,
      "train_loss": 4.75254754225413,
      "train_runtime": 23.8349,
      "train_samples_per_second": 11.202,
      "train_steps_per_second": 0.252
    }
  ],
  "logging_steps": 5,
  "max_steps": 6,
  "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": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 388288208699392.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}