{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1053740779768177,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002107481559536354,
      "eval_loss": 1.3075774908065796,
      "eval_runtime": 11.6726,
      "eval_samples_per_second": 17.134,
      "eval_steps_per_second": 8.567,
      "step": 1
    },
    {
      "epoch": 0.01053740779768177,
      "grad_norm": 1.3717970848083496,
      "learning_rate": 5e-05,
      "loss": 1.5109,
      "step": 5
    },
    {
      "epoch": 0.02107481559536354,
      "grad_norm": 1.5167689323425293,
      "learning_rate": 0.0001,
      "loss": 1.1535,
      "step": 10
    },
    {
      "epoch": 0.02107481559536354,
      "eval_loss": 1.0952444076538086,
      "eval_runtime": 11.7408,
      "eval_samples_per_second": 17.035,
      "eval_steps_per_second": 8.517,
      "step": 10
    },
    {
      "epoch": 0.03161222339304531,
      "grad_norm": 1.737998366355896,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.8695,
      "step": 15
    },
    {
      "epoch": 0.04214963119072708,
      "grad_norm": 1.6746647357940674,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.5502,
      "step": 20
    },
    {
      "epoch": 0.04214963119072708,
      "eval_loss": 0.5695419907569885,
      "eval_runtime": 11.944,
      "eval_samples_per_second": 16.745,
      "eval_steps_per_second": 8.372,
      "step": 20
    },
    {
      "epoch": 0.05268703898840885,
      "grad_norm": 1.2471041679382324,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.5161,
      "step": 25
    },
    {
      "epoch": 0.06322444678609063,
      "grad_norm": 1.1821861267089844,
      "learning_rate": 5e-05,
      "loss": 0.4126,
      "step": 30
    },
    {
      "epoch": 0.06322444678609063,
      "eval_loss": 0.44907933473587036,
      "eval_runtime": 12.0976,
      "eval_samples_per_second": 16.532,
      "eval_steps_per_second": 8.266,
      "step": 30
    },
    {
      "epoch": 0.0737618545837724,
      "grad_norm": 2.788278818130493,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.5542,
      "step": 35
    },
    {
      "epoch": 0.08429926238145416,
      "grad_norm": 2.504286050796509,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.4188,
      "step": 40
    },
    {
      "epoch": 0.08429926238145416,
      "eval_loss": 0.4098703861236572,
      "eval_runtime": 12.3412,
      "eval_samples_per_second": 16.206,
      "eval_steps_per_second": 8.103,
      "step": 40
    },
    {
      "epoch": 0.09483667017913593,
      "grad_norm": 2.0990967750549316,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.3859,
      "step": 45
    },
    {
      "epoch": 0.1053740779768177,
      "grad_norm": 1.518781304359436,
      "learning_rate": 0.0,
      "loss": 0.4902,
      "step": 50
    },
    {
      "epoch": 0.1053740779768177,
      "eval_loss": 0.4010012745857239,
      "eval_runtime": 11.8458,
      "eval_samples_per_second": 16.884,
      "eval_steps_per_second": 8.442,
      "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": 8143670712729600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}