{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002458462231873963,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.194874106246543e-05,
      "eval_loss": 11.113255500793457,
      "eval_runtime": 25.1846,
      "eval_samples_per_second": 204.013,
      "eval_steps_per_second": 102.007,
      "step": 1
    },
    {
      "epoch": 0.0002458462231873963,
      "grad_norm": 1.3255553245544434,
      "learning_rate": 3e-05,
      "loss": 44.4184,
      "step": 3
    },
    {
      "epoch": 0.0004916924463747926,
      "grad_norm": 1.1339774131774902,
      "learning_rate": 6e-05,
      "loss": 44.4746,
      "step": 6
    },
    {
      "epoch": 0.0006555899284997234,
      "eval_loss": 11.111296653747559,
      "eval_runtime": 25.3916,
      "eval_samples_per_second": 202.35,
      "eval_steps_per_second": 101.175,
      "step": 8
    },
    {
      "epoch": 0.0007375386695621888,
      "grad_norm": 1.3766000270843506,
      "learning_rate": 9e-05,
      "loss": 44.4632,
      "step": 9
    },
    {
      "epoch": 0.000983384892749585,
      "grad_norm": 1.1705154180526733,
      "learning_rate": 9.755282581475769e-05,
      "loss": 44.4095,
      "step": 12
    },
    {
      "epoch": 0.0012292311159369815,
      "grad_norm": 1.2520356178283691,
      "learning_rate": 8.535533905932738e-05,
      "loss": 44.4302,
      "step": 15
    },
    {
      "epoch": 0.0013111798569994469,
      "eval_loss": 11.104732513427734,
      "eval_runtime": 25.3579,
      "eval_samples_per_second": 202.619,
      "eval_steps_per_second": 101.31,
      "step": 16
    },
    {
      "epoch": 0.0014750773391243777,
      "grad_norm": 1.2990171909332275,
      "learning_rate": 6.545084971874738e-05,
      "loss": 44.4028,
      "step": 18
    },
    {
      "epoch": 0.001720923562311774,
      "grad_norm": 1.2452588081359863,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 44.4156,
      "step": 21
    },
    {
      "epoch": 0.00196676978549917,
      "grad_norm": 1.3686741590499878,
      "learning_rate": 2.061073738537635e-05,
      "loss": 44.3663,
      "step": 24
    },
    {
      "epoch": 0.00196676978549917,
      "eval_loss": 11.100367546081543,
      "eval_runtime": 25.1832,
      "eval_samples_per_second": 204.025,
      "eval_steps_per_second": 102.012,
      "step": 24
    },
    {
      "epoch": 0.0022126160086865664,
      "grad_norm": 1.308458924293518,
      "learning_rate": 5.449673790581611e-06,
      "loss": 44.3951,
      "step": 27
    },
    {
      "epoch": 0.002458462231873963,
      "grad_norm": 1.25251042842865,
      "learning_rate": 0.0,
      "loss": 44.399,
      "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": 623986606080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}