{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3,
  "eval_steps": 150,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "grad_norm": 4757.10498046875,
      "learning_rate": 3.2666666666666663e-07,
      "loss": 74.4742,
      "step": 50
    },
    {
      "epoch": 0.1,
      "grad_norm": 15446.2177734375,
      "learning_rate": 6.6e-07,
      "loss": 74.3892,
      "step": 100
    },
    {
      "epoch": 0.15,
      "grad_norm": 6237.49609375,
      "learning_rate": 9.933333333333333e-07,
      "loss": 74.3298,
      "step": 150
    },
    {
      "epoch": 0.15,
      "eval_accuracy": 0.25207497151999875,
      "eval_loss": 4.663373947143555,
      "eval_runtime": 6.2495,
      "eval_samples_per_second": 80.007,
      "eval_steps_per_second": 1.28,
      "step": 150
    },
    {
      "epoch": 0.2,
      "grad_norm": 5204.32177734375,
      "learning_rate": 9.91822760447871e-07,
      "loss": 74.1263,
      "step": 200
    },
    {
      "epoch": 0.25,
      "grad_norm": 3447.847412109375,
      "learning_rate": 9.66900501749214e-07,
      "loss": 74.1159,
      "step": 250
    },
    {
      "epoch": 0.3,
      "grad_norm": 7081.478515625,
      "learning_rate": 9.26078506448917e-07,
      "loss": 73.7028,
      "step": 300
    },
    {
      "epoch": 0.3,
      "eval_accuracy": 0.2524926128464903,
      "eval_loss": 4.656529903411865,
      "eval_runtime": 6.2929,
      "eval_samples_per_second": 79.455,
      "eval_steps_per_second": 1.271,
      "step": 300
    }
  ],
  "logging_steps": 50,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 150,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}