{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1053740779768177,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01053740779768177,
      "grad_norm": 3.070249080657959,
      "learning_rate": 4.982437653670531e-05,
      "loss": 1.7879,
      "step": 10
    },
    {
      "epoch": 0.02107481559536354,
      "grad_norm": 1.702326774597168,
      "learning_rate": 4.964875307341061e-05,
      "loss": 0.5567,
      "step": 20
    },
    {
      "epoch": 0.03161222339304531,
      "grad_norm": 1.1947294473648071,
      "learning_rate": 4.947312961011591e-05,
      "loss": 0.4493,
      "step": 30
    },
    {
      "epoch": 0.04214963119072708,
      "grad_norm": 0.9556658267974854,
      "learning_rate": 4.929750614682122e-05,
      "loss": 0.3728,
      "step": 40
    },
    {
      "epoch": 0.05268703898840885,
      "grad_norm": 0.7952510714530945,
      "learning_rate": 4.9121882683526524e-05,
      "loss": 0.3535,
      "step": 50
    },
    {
      "epoch": 0.05268703898840885,
      "eval_loss": 0.4311191439628601,
      "eval_runtime": 13.6539,
      "eval_samples_per_second": 35.155,
      "eval_steps_per_second": 2.197,
      "step": 50
    },
    {
      "epoch": 0.06322444678609063,
      "grad_norm": 0.6962826251983643,
      "learning_rate": 4.894625922023183e-05,
      "loss": 0.3507,
      "step": 60
    },
    {
      "epoch": 0.0737618545837724,
      "grad_norm": 0.6941961646080017,
      "learning_rate": 4.877063575693713e-05,
      "loss": 0.3585,
      "step": 70
    },
    {
      "epoch": 0.08429926238145416,
      "grad_norm": 0.6864392757415771,
      "learning_rate": 4.8595012293642434e-05,
      "loss": 0.3496,
      "step": 80
    },
    {
      "epoch": 0.09483667017913593,
      "grad_norm": 0.7322937846183777,
      "learning_rate": 4.841938883034774e-05,
      "loss": 0.3295,
      "step": 90
    },
    {
      "epoch": 0.1053740779768177,
      "grad_norm": 0.6921488046646118,
      "learning_rate": 4.824376536705304e-05,
      "loss": 0.3357,
      "step": 100
    },
    {
      "epoch": 0.1053740779768177,
      "eval_loss": 0.39120009541511536,
      "eval_runtime": 13.7031,
      "eval_samples_per_second": 35.029,
      "eval_steps_per_second": 2.189,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 2847,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1795573109030912e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}