{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0001659000700927796,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6590007009277963e-05,
      "grad_norm": 7.927350044250488,
      "learning_rate": 2e-05,
      "loss": 4.2896,
      "step": 1
    },
    {
      "epoch": 1.6590007009277963e-05,
      "eval_loss": 5.197057723999023,
      "eval_runtime": 889.1241,
      "eval_samples_per_second": 28.545,
      "eval_steps_per_second": 14.272,
      "step": 1
    },
    {
      "epoch": 3.3180014018555926e-05,
      "grad_norm": 12.704501152038574,
      "learning_rate": 4e-05,
      "loss": 6.3113,
      "step": 2
    },
    {
      "epoch": 4.9770021027833886e-05,
      "grad_norm": 9.076577186584473,
      "learning_rate": 6e-05,
      "loss": 5.0651,
      "step": 3
    },
    {
      "epoch": 4.9770021027833886e-05,
      "eval_loss": 5.08416223526001,
      "eval_runtime": 889.6814,
      "eval_samples_per_second": 28.527,
      "eval_steps_per_second": 14.264,
      "step": 3
    },
    {
      "epoch": 6.636002803711185e-05,
      "grad_norm": 7.2819294929504395,
      "learning_rate": 8e-05,
      "loss": 4.5399,
      "step": 4
    },
    {
      "epoch": 8.29500350463898e-05,
      "grad_norm": 12.246438026428223,
      "learning_rate": 0.0001,
      "loss": 5.6969,
      "step": 5
    },
    {
      "epoch": 9.954004205566777e-05,
      "grad_norm": 10.355069160461426,
      "learning_rate": 0.00012,
      "loss": 4.5522,
      "step": 6
    },
    {
      "epoch": 9.954004205566777e-05,
      "eval_loss": 3.8390557765960693,
      "eval_runtime": 890.0993,
      "eval_samples_per_second": 28.514,
      "eval_steps_per_second": 14.257,
      "step": 6
    },
    {
      "epoch": 0.00011613004906494572,
      "grad_norm": 10.04697322845459,
      "learning_rate": 0.00014,
      "loss": 3.3826,
      "step": 7
    },
    {
      "epoch": 0.0001327200560742237,
      "grad_norm": 7.710323810577393,
      "learning_rate": 0.00016,
      "loss": 2.6396,
      "step": 8
    },
    {
      "epoch": 0.00014931006308350166,
      "grad_norm": 10.670214653015137,
      "learning_rate": 0.00018,
      "loss": 2.8912,
      "step": 9
    },
    {
      "epoch": 0.00014931006308350166,
      "eval_loss": 2.3122751712799072,
      "eval_runtime": 889.6427,
      "eval_samples_per_second": 28.528,
      "eval_steps_per_second": 14.264,
      "step": 9
    },
    {
      "epoch": 0.0001659000700927796,
      "grad_norm": 7.535514831542969,
      "learning_rate": 0.0002,
      "loss": 2.1857,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1911091416268800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}