{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1768346595932803,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0035366931918656055,
      "eval_loss": 7.848944664001465,
      "eval_runtime": 13.8388,
      "eval_samples_per_second": 8.671,
      "eval_steps_per_second": 4.336,
      "step": 1
    },
    {
      "epoch": 0.01768346595932803,
      "grad_norm": 4.622712135314941,
      "learning_rate": 5e-05,
      "loss": 8.1335,
      "step": 5
    },
    {
      "epoch": 0.03536693191865606,
      "grad_norm": 9.629229545593262,
      "learning_rate": 0.0001,
      "loss": 7.2117,
      "step": 10
    },
    {
      "epoch": 0.03536693191865606,
      "eval_loss": 5.49931526184082,
      "eval_runtime": 14.0899,
      "eval_samples_per_second": 8.517,
      "eval_steps_per_second": 4.258,
      "step": 10
    },
    {
      "epoch": 0.05305039787798409,
      "grad_norm": 9.621377944946289,
      "learning_rate": 9.619397662556435e-05,
      "loss": 4.1185,
      "step": 15
    },
    {
      "epoch": 0.07073386383731212,
      "grad_norm": 2.8658766746520996,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.4235,
      "step": 20
    },
    {
      "epoch": 0.07073386383731212,
      "eval_loss": 0.8843831419944763,
      "eval_runtime": 14.1818,
      "eval_samples_per_second": 8.462,
      "eval_steps_per_second": 4.231,
      "step": 20
    },
    {
      "epoch": 0.08841732979664015,
      "grad_norm": 2.0114266872406006,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.842,
      "step": 25
    },
    {
      "epoch": 0.10610079575596817,
      "grad_norm": 4.434057712554932,
      "learning_rate": 5e-05,
      "loss": 1.0252,
      "step": 30
    },
    {
      "epoch": 0.10610079575596817,
      "eval_loss": 0.8172988891601562,
      "eval_runtime": 14.1194,
      "eval_samples_per_second": 8.499,
      "eval_steps_per_second": 4.249,
      "step": 30
    },
    {
      "epoch": 0.1237842617152962,
      "grad_norm": 4.096339225769043,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.6784,
      "step": 35
    },
    {
      "epoch": 0.14146772767462423,
      "grad_norm": 2.1522183418273926,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.7385,
      "step": 40
    },
    {
      "epoch": 0.14146772767462423,
      "eval_loss": 0.8148200511932373,
      "eval_runtime": 14.3401,
      "eval_samples_per_second": 8.368,
      "eval_steps_per_second": 4.184,
      "step": 40
    },
    {
      "epoch": 0.15915119363395225,
      "grad_norm": 1.3055857419967651,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.7619,
      "step": 45
    },
    {
      "epoch": 0.1768346595932803,
      "grad_norm": 2.882671356201172,
      "learning_rate": 0.0,
      "loss": 0.855,
      "step": 50
    },
    {
      "epoch": 0.1768346595932803,
      "eval_loss": 0.8008769154548645,
      "eval_runtime": 14.0692,
      "eval_samples_per_second": 8.529,
      "eval_steps_per_second": 4.265,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8362701336084480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}