{
  "best_metric": 0.5010046362876892,
  "best_model_checkpoint": "/home/ankur/projects/llm_test/Akshay/fine_tuning/llama_3.1_snippets_v3/checkpoint-2574",
  "epoch": 2.9994173625946785,
  "eval_steps": 500,
  "global_step": 2574,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9998057875315596,
      "grad_norm": 0.1494140625,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.6069,
      "step": 858
    },
    {
      "epoch": 0.9998057875315596,
      "eval_loss": 0.5826191902160645,
      "eval_runtime": 814.9742,
      "eval_samples_per_second": 3.145,
      "eval_steps_per_second": 1.573,
      "step": 858
    },
    {
      "epoch": 1.9996115750631192,
      "grad_norm": 0.2119140625,
      "learning_rate": 0.0001,
      "loss": 0.5,
      "step": 1716
    },
    {
      "epoch": 1.9996115750631192,
      "eval_loss": 0.5274960398674011,
      "eval_runtime": 813.6647,
      "eval_samples_per_second": 3.15,
      "eval_steps_per_second": 1.576,
      "step": 1716
    },
    {
      "epoch": 2.9994173625946785,
      "grad_norm": 0.302734375,
      "learning_rate": 5e-05,
      "loss": 0.3825,
      "step": 2574
    },
    {
      "epoch": 2.9994173625946785,
      "eval_loss": 0.5010046362876892,
      "eval_runtime": 811.606,
      "eval_samples_per_second": 3.158,
      "eval_steps_per_second": 1.58,
      "step": 2574
    }
  ],
  "logging_steps": 500,
  "max_steps": 3432,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.244335641581158e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}