{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.017640573318632856,
  "eval_steps": 5,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0035281146637265713,
      "grad_norm": 4.04030704498291,
      "learning_rate": 1e-05,
      "loss": 4.1831,
      "step": 1
    },
    {
      "epoch": 0.0035281146637265713,
      "eval_loss": 4.5313615798950195,
      "eval_runtime": 56.8526,
      "eval_samples_per_second": 8.408,
      "eval_steps_per_second": 4.204,
      "step": 1
    },
    {
      "epoch": 0.0070562293274531425,
      "grad_norm": 3.4920718669891357,
      "learning_rate": 2e-05,
      "loss": 4.2023,
      "step": 2
    },
    {
      "epoch": 0.010584343991179712,
      "grad_norm": 4.01487398147583,
      "learning_rate": 3e-05,
      "loss": 4.4356,
      "step": 3
    },
    {
      "epoch": 0.014112458654906285,
      "grad_norm": 4.010401725769043,
      "learning_rate": 4e-05,
      "loss": 4.2765,
      "step": 4
    },
    {
      "epoch": 0.017640573318632856,
      "grad_norm": 3.706618070602417,
      "learning_rate": 5e-05,
      "loss": 4.126,
      "step": 5
    },
    {
      "epoch": 0.017640573318632856,
      "eval_loss": 4.215136528015137,
      "eval_runtime": 12.1488,
      "eval_samples_per_second": 39.346,
      "eval_steps_per_second": 19.673,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3822182832537600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}