{
  "best_metric": 0.6730473637580872,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.03487358326068003,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011624527753560012,
      "eval_loss": 0.8452630043029785,
      "eval_runtime": 28.1332,
      "eval_samples_per_second": 12.903,
      "eval_steps_per_second": 6.469,
      "step": 1
    },
    {
      "epoch": 0.0034873583260680036,
      "grad_norm": 1.0308128595352173,
      "learning_rate": 6e-05,
      "loss": 3.2779,
      "step": 3
    },
    {
      "epoch": 0.005812263876780006,
      "eval_loss": 0.8282259106636047,
      "eval_runtime": 28.4239,
      "eval_samples_per_second": 12.771,
      "eval_steps_per_second": 6.403,
      "step": 5
    },
    {
      "epoch": 0.006974716652136007,
      "grad_norm": 1.3154348134994507,
      "learning_rate": 0.00012,
      "loss": 3.4687,
      "step": 6
    },
    {
      "epoch": 0.010462074978204011,
      "grad_norm": 1.4607170820236206,
      "learning_rate": 0.00018,
      "loss": 3.363,
      "step": 9
    },
    {
      "epoch": 0.011624527753560012,
      "eval_loss": 0.752495527267456,
      "eval_runtime": 28.3871,
      "eval_samples_per_second": 12.787,
      "eval_steps_per_second": 6.411,
      "step": 10
    },
    {
      "epoch": 0.013949433304272014,
      "grad_norm": 1.771251916885376,
      "learning_rate": 0.00019510565162951537,
      "loss": 3.0502,
      "step": 12
    },
    {
      "epoch": 0.017436791630340016,
      "grad_norm": 1.7839971780776978,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.8952,
      "step": 15
    },
    {
      "epoch": 0.017436791630340016,
      "eval_loss": 0.7082406878471375,
      "eval_runtime": 28.4197,
      "eval_samples_per_second": 12.773,
      "eval_steps_per_second": 6.404,
      "step": 15
    },
    {
      "epoch": 0.020924149956408022,
      "grad_norm": 1.599076271057129,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.8691,
      "step": 18
    },
    {
      "epoch": 0.023249055507120024,
      "eval_loss": 0.684432327747345,
      "eval_runtime": 28.4133,
      "eval_samples_per_second": 12.776,
      "eval_steps_per_second": 6.405,
      "step": 20
    },
    {
      "epoch": 0.024411508282476024,
      "grad_norm": 1.189245343208313,
      "learning_rate": 8.435655349597689e-05,
      "loss": 2.6574,
      "step": 21
    },
    {
      "epoch": 0.02789886660854403,
      "grad_norm": 2.2764976024627686,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.6139,
      "step": 24
    },
    {
      "epoch": 0.02906131938390003,
      "eval_loss": 0.6749742031097412,
      "eval_runtime": 28.4368,
      "eval_samples_per_second": 12.765,
      "eval_steps_per_second": 6.4,
      "step": 25
    },
    {
      "epoch": 0.03138622493461203,
      "grad_norm": 1.5035099983215332,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.5178,
      "step": 27
    },
    {
      "epoch": 0.03487358326068003,
      "grad_norm": 1.2478257417678833,
      "learning_rate": 0.0,
      "loss": 2.8392,
      "step": 30
    },
    {
      "epoch": 0.03487358326068003,
      "eval_loss": 0.6730473637580872,
      "eval_runtime": 28.4323,
      "eval_samples_per_second": 12.767,
      "eval_steps_per_second": 6.401,
      "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": 1.0210284404736e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}