{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0009008603216071348,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.0028677386904494e-05,
      "eval_loss": 1.0328869819641113,
      "eval_runtime": 1647.1723,
      "eval_samples_per_second": 8.513,
      "eval_steps_per_second": 4.256,
      "step": 1
    },
    {
      "epoch": 9.008603216071348e-05,
      "grad_norm": 0.2662915587425232,
      "learning_rate": 3e-05,
      "loss": 0.965,
      "step": 3
    },
    {
      "epoch": 0.00015014338693452247,
      "eval_loss": 1.0183448791503906,
      "eval_runtime": 1647.4187,
      "eval_samples_per_second": 8.511,
      "eval_steps_per_second": 4.256,
      "step": 5
    },
    {
      "epoch": 0.00018017206432142696,
      "grad_norm": 0.44537869095802307,
      "learning_rate": 6e-05,
      "loss": 0.9669,
      "step": 6
    },
    {
      "epoch": 0.0002702580964821404,
      "grad_norm": 0.6517441868782043,
      "learning_rate": 9e-05,
      "loss": 0.9603,
      "step": 9
    },
    {
      "epoch": 0.00030028677386904494,
      "eval_loss": 0.8726487159729004,
      "eval_runtime": 1647.1028,
      "eval_samples_per_second": 8.513,
      "eval_steps_per_second": 4.257,
      "step": 10
    },
    {
      "epoch": 0.00036034412864285393,
      "grad_norm": 0.27762144804000854,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7966,
      "step": 12
    },
    {
      "epoch": 0.0004504301608035674,
      "grad_norm": 0.4063872694969177,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.7659,
      "step": 15
    },
    {
      "epoch": 0.0004504301608035674,
      "eval_loss": 0.7490118741989136,
      "eval_runtime": 1647.3075,
      "eval_samples_per_second": 8.512,
      "eval_steps_per_second": 4.256,
      "step": 15
    },
    {
      "epoch": 0.0005405161929642808,
      "grad_norm": 0.29023927450180054,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7313,
      "step": 18
    },
    {
      "epoch": 0.0006005735477380899,
      "eval_loss": 0.6987407803535461,
      "eval_runtime": 1647.474,
      "eval_samples_per_second": 8.511,
      "eval_steps_per_second": 4.256,
      "step": 20
    },
    {
      "epoch": 0.0006306022251249943,
      "grad_norm": 0.30331218242645264,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.6797,
      "step": 21
    },
    {
      "epoch": 0.0007206882572857079,
      "grad_norm": 0.2817479074001312,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6745,
      "step": 24
    },
    {
      "epoch": 0.0007507169346726123,
      "eval_loss": 0.6795505881309509,
      "eval_runtime": 1647.8113,
      "eval_samples_per_second": 8.509,
      "eval_steps_per_second": 4.255,
      "step": 25
    },
    {
      "epoch": 0.0008107742894464214,
      "grad_norm": 0.25237756967544556,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.7254,
      "step": 27
    },
    {
      "epoch": 0.0009008603216071348,
      "grad_norm": 0.2647419273853302,
      "learning_rate": 0.0,
      "loss": 0.6637,
      "step": 30
    },
    {
      "epoch": 0.0009008603216071348,
      "eval_loss": 0.6759388446807861,
      "eval_runtime": 1647.7113,
      "eval_samples_per_second": 8.51,
      "eval_steps_per_second": 4.255,
      "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": 2.47563798183936e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}