{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0015113159783881815,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.037719927960605e-05,
      "eval_loss": 2.1698710918426514,
      "eval_runtime": 478.167,
      "eval_samples_per_second": 17.479,
      "eval_steps_per_second": 8.74,
      "step": 1
    },
    {
      "epoch": 0.00015113159783881815,
      "grad_norm": 0.9233885407447815,
      "learning_rate": 3e-05,
      "loss": 2.0529,
      "step": 3
    },
    {
      "epoch": 0.0003022631956776363,
      "grad_norm": 1.3138552904129028,
      "learning_rate": 6e-05,
      "loss": 2.237,
      "step": 6
    },
    {
      "epoch": 0.0004030175942368484,
      "eval_loss": 2.0824451446533203,
      "eval_runtime": 477.5189,
      "eval_samples_per_second": 17.503,
      "eval_steps_per_second": 8.751,
      "step": 8
    },
    {
      "epoch": 0.00045339479351645445,
      "grad_norm": 1.2923656702041626,
      "learning_rate": 9e-05,
      "loss": 2.2233,
      "step": 9
    },
    {
      "epoch": 0.0006045263913552726,
      "grad_norm": 1.2511311769485474,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.8121,
      "step": 12
    },
    {
      "epoch": 0.0007556579891940908,
      "grad_norm": 1.166586995124817,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.6843,
      "step": 15
    },
    {
      "epoch": 0.0008060351884736968,
      "eval_loss": 1.806187391281128,
      "eval_runtime": 477.6935,
      "eval_samples_per_second": 17.497,
      "eval_steps_per_second": 8.748,
      "step": 16
    },
    {
      "epoch": 0.0009067895870329089,
      "grad_norm": 1.883200764656067,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.8519,
      "step": 18
    },
    {
      "epoch": 0.0010579211848717272,
      "grad_norm": 1.3882564306259155,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 1.7061,
      "step": 21
    },
    {
      "epoch": 0.0012090527827105452,
      "grad_norm": 1.8157745599746704,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.7379,
      "step": 24
    },
    {
      "epoch": 0.0012090527827105452,
      "eval_loss": 1.7392501831054688,
      "eval_runtime": 478.4663,
      "eval_samples_per_second": 17.468,
      "eval_steps_per_second": 8.734,
      "step": 24
    },
    {
      "epoch": 0.0013601843805493635,
      "grad_norm": 1.3854663372039795,
      "learning_rate": 5.449673790581611e-06,
      "loss": 1.6428,
      "step": 27
    },
    {
      "epoch": 0.0015113159783881815,
      "grad_norm": 1.552529215812683,
      "learning_rate": 0.0,
      "loss": 1.5177,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.112830925340672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}