{
  "best_metric": 1.901120901107788,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0025311115798354778,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.437038599451593e-05,
      "eval_loss": 5.567965984344482,
      "eval_runtime": 985.8286,
      "eval_samples_per_second": 5.063,
      "eval_steps_per_second": 2.532,
      "step": 1
    },
    {
      "epoch": 0.0002531111579835478,
      "grad_norm": 20.080171585083008,
      "learning_rate": 0.00012,
      "loss": 4.9486,
      "step": 3
    },
    {
      "epoch": 0.0004218519299725796,
      "eval_loss": 2.663083791732788,
      "eval_runtime": 991.4461,
      "eval_samples_per_second": 5.034,
      "eval_steps_per_second": 2.518,
      "step": 5
    },
    {
      "epoch": 0.0005062223159670956,
      "grad_norm": 2.0364084243774414,
      "learning_rate": 0.0001992114701314478,
      "loss": 3.2361,
      "step": 6
    },
    {
      "epoch": 0.0007593334739506433,
      "grad_norm": 1.9081493616104126,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.4302,
      "step": 9
    },
    {
      "epoch": 0.0008437038599451593,
      "eval_loss": 2.1014163494110107,
      "eval_runtime": 991.3422,
      "eval_samples_per_second": 5.035,
      "eval_steps_per_second": 2.518,
      "step": 10
    },
    {
      "epoch": 0.001012444631934191,
      "grad_norm": 1.591448426246643,
      "learning_rate": 0.000163742398974869,
      "loss": 2.2339,
      "step": 12
    },
    {
      "epoch": 0.0012655557899177389,
      "grad_norm": 1.1119730472564697,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.9852,
      "step": 15
    },
    {
      "epoch": 0.0012655557899177389,
      "eval_loss": 1.9696526527404785,
      "eval_runtime": 993.3758,
      "eval_samples_per_second": 5.024,
      "eval_steps_per_second": 2.513,
      "step": 15
    },
    {
      "epoch": 0.0015186669479012867,
      "grad_norm": 1.175823450088501,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.9316,
      "step": 18
    },
    {
      "epoch": 0.0016874077198903185,
      "eval_loss": 1.9246728420257568,
      "eval_runtime": 997.3563,
      "eval_samples_per_second": 5.004,
      "eval_steps_per_second": 2.503,
      "step": 20
    },
    {
      "epoch": 0.0017717781058848344,
      "grad_norm": 1.0983132123947144,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.029,
      "step": 21
    },
    {
      "epoch": 0.002024889263868382,
      "grad_norm": 0.9510492086410522,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.8694,
      "step": 24
    },
    {
      "epoch": 0.002109259649862898,
      "eval_loss": 1.904327392578125,
      "eval_runtime": 992.4963,
      "eval_samples_per_second": 5.029,
      "eval_steps_per_second": 2.515,
      "step": 25
    },
    {
      "epoch": 0.0022780004218519298,
      "grad_norm": 1.0499024391174316,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.876,
      "step": 27
    },
    {
      "epoch": 0.0025311115798354778,
      "grad_norm": 1.0561531782150269,
      "learning_rate": 0.0,
      "loss": 1.911,
      "step": 30
    },
    {
      "epoch": 0.0025311115798354778,
      "eval_loss": 1.901120901107788,
      "eval_runtime": 991.5024,
      "eval_samples_per_second": 5.034,
      "eval_steps_per_second": 2.517,
      "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": 1.235418813038592e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}