{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01934984520123839,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003869969040247678,
      "eval_loss": 1.4191824197769165,
      "eval_runtime": 108.3853,
      "eval_samples_per_second": 2.657,
      "eval_steps_per_second": 2.657,
      "step": 1
    },
    {
      "epoch": 0.001934984520123839,
      "grad_norm": 0.5994939804077148,
      "learning_rate": 5e-05,
      "loss": 1.3098,
      "step": 5
    },
    {
      "epoch": 0.003869969040247678,
      "grad_norm": 0.5028858184814453,
      "learning_rate": 0.0001,
      "loss": 1.4769,
      "step": 10
    },
    {
      "epoch": 0.005804953560371517,
      "grad_norm": 0.5422282218933105,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.2964,
      "step": 15
    },
    {
      "epoch": 0.007739938080495356,
      "grad_norm": 0.5431628823280334,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.305,
      "step": 20
    },
    {
      "epoch": 0.009674922600619196,
      "grad_norm": 0.4320271611213684,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.2359,
      "step": 25
    },
    {
      "epoch": 0.009674922600619196,
      "eval_loss": 1.2999417781829834,
      "eval_runtime": 108.2878,
      "eval_samples_per_second": 2.66,
      "eval_steps_per_second": 2.66,
      "step": 25
    },
    {
      "epoch": 0.011609907120743035,
      "grad_norm": 0.41392597556114197,
      "learning_rate": 5e-05,
      "loss": 1.3273,
      "step": 30
    },
    {
      "epoch": 0.013544891640866873,
      "grad_norm": 0.47019708156585693,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.2684,
      "step": 35
    },
    {
      "epoch": 0.015479876160990712,
      "grad_norm": 0.477716326713562,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.2093,
      "step": 40
    },
    {
      "epoch": 0.01741486068111455,
      "grad_norm": 0.4382253587245941,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.218,
      "step": 45
    },
    {
      "epoch": 0.01934984520123839,
      "grad_norm": 0.4909341335296631,
      "learning_rate": 0.0,
      "loss": 1.3078,
      "step": 50
    },
    {
      "epoch": 0.01934984520123839,
      "eval_loss": 1.281789779663086,
      "eval_runtime": 108.7097,
      "eval_samples_per_second": 2.649,
      "eval_steps_per_second": 2.649,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3318875978465280.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}