{
  "best_global_step": 10,
  "best_metric": 0.016629977151751518,
  "best_model_checkpoint": "allrun_script_results/checkpoint-10",
  "epoch": 3.0,
  "eval_steps": 10,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 0.7041864209695657,
      "learning_rate": 0.0004,
      "loss": 0.1443,
      "step": 2
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.6003273417765542,
      "learning_rate": 0.00036923076923076927,
      "loss": 0.1237,
      "step": 4
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.15366755081544378,
      "learning_rate": 0.0003076923076923077,
      "loss": 0.0406,
      "step": 6
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.09797976242867891,
      "learning_rate": 0.0002461538461538462,
      "loss": 0.025,
      "step": 8
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.05168178043033845,
      "learning_rate": 0.00018461538461538463,
      "loss": 0.0225,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9926975072400843,
      "eval_loss": 0.016629977151751518,
      "eval_runtime": 70.6518,
      "eval_samples_per_second": 0.467,
      "eval_steps_per_second": 0.071,
      "step": 10
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.02737186313370043,
      "learning_rate": 0.0001230769230769231,
      "loss": 0.0154,
      "step": 12
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.024063335363276064,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.0166,
      "step": 14
    },
    {
      "epoch": 3.0,
      "step": 15,
      "total_flos": 5770520297472.0,
      "train_loss": 0.05250408972303073,
      "train_runtime": 1174.2388,
      "train_samples_per_second": 0.199,
      "train_steps_per_second": 0.013
    }
  ],
  "logging_steps": 2,
  "max_steps": 15,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5770520297472.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}