{
  "best_metric": 2.2300872802734375,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.06109979633401222,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002036659877800407,
      "eval_loss": 3.4811758995056152,
      "eval_runtime": 13.4844,
      "eval_samples_per_second": 30.702,
      "eval_steps_per_second": 7.713,
      "step": 1
    },
    {
      "epoch": 0.006109979633401222,
      "grad_norm": 7.875271320343018,
      "learning_rate": 0.00012,
      "loss": 10.9052,
      "step": 3
    },
    {
      "epoch": 0.010183299389002037,
      "eval_loss": 3.100127696990967,
      "eval_runtime": 13.5378,
      "eval_samples_per_second": 30.581,
      "eval_steps_per_second": 7.682,
      "step": 5
    },
    {
      "epoch": 0.012219959266802444,
      "grad_norm": 4.054202079772949,
      "learning_rate": 0.0001992114701314478,
      "loss": 10.9559,
      "step": 6
    },
    {
      "epoch": 0.018329938900203666,
      "grad_norm": 3.9465723037719727,
      "learning_rate": 0.00018763066800438636,
      "loss": 10.27,
      "step": 9
    },
    {
      "epoch": 0.020366598778004074,
      "eval_loss": 2.640319585800171,
      "eval_runtime": 13.5635,
      "eval_samples_per_second": 30.523,
      "eval_steps_per_second": 7.668,
      "step": 10
    },
    {
      "epoch": 0.024439918533604887,
      "grad_norm": 4.1958842277526855,
      "learning_rate": 0.000163742398974869,
      "loss": 10.154,
      "step": 12
    },
    {
      "epoch": 0.03054989816700611,
      "grad_norm": 4.309093952178955,
      "learning_rate": 0.00013090169943749476,
      "loss": 9.6833,
      "step": 15
    },
    {
      "epoch": 0.03054989816700611,
      "eval_loss": 2.373173236846924,
      "eval_runtime": 13.5832,
      "eval_samples_per_second": 30.479,
      "eval_steps_per_second": 7.657,
      "step": 15
    },
    {
      "epoch": 0.03665987780040733,
      "grad_norm": 3.6466476917266846,
      "learning_rate": 9.372094804706867e-05,
      "loss": 8.9575,
      "step": 18
    },
    {
      "epoch": 0.04073319755600815,
      "eval_loss": 2.2733120918273926,
      "eval_runtime": 13.6449,
      "eval_samples_per_second": 30.341,
      "eval_steps_per_second": 7.622,
      "step": 20
    },
    {
      "epoch": 0.04276985743380855,
      "grad_norm": 3.9431509971618652,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 9.1226,
      "step": 21
    },
    {
      "epoch": 0.048879837067209775,
      "grad_norm": 3.7178170680999756,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 8.6709,
      "step": 24
    },
    {
      "epoch": 0.05091649694501019,
      "eval_loss": 2.2334296703338623,
      "eval_runtime": 13.6481,
      "eval_samples_per_second": 30.334,
      "eval_steps_per_second": 7.62,
      "step": 25
    },
    {
      "epoch": 0.054989816700611,
      "grad_norm": 3.574514627456665,
      "learning_rate": 7.022351411174866e-06,
      "loss": 8.4494,
      "step": 27
    },
    {
      "epoch": 0.06109979633401222,
      "grad_norm": 3.8659167289733887,
      "learning_rate": 0.0,
      "loss": 8.9901,
      "step": 30
    },
    {
      "epoch": 0.06109979633401222,
      "eval_loss": 2.2300872802734375,
      "eval_runtime": 13.6637,
      "eval_samples_per_second": 30.299,
      "eval_steps_per_second": 7.611,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 910112965263360.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}